This paper presents our latest investigation on end-to-end automatic speech recognition (ASR) for overlapped speech. We propose to train an end-to-end system conditioned on speaker embeddings and further improved by transfer learning from clean speech. This proposed framework does not require any parallel non-overlapped speech materials and is independent of the number of speakers. Our experimental results on overlapped speech datasets show that joint conditioning on speaker embeddings and transfer learning significantly improves the ASR performance.
We propose an end-to-end speaker-attributed automatic speech recognition model that unifies speaker counting, speech recognition, and speaker identification on monaural overlapped speech. Our model is built on serialized output training (SOT) with attention-based encoder-decoder, a recently proposed method for recognizing overlapped speech comprising an arbitrary number of speakers. We extend SOT by introducing a speaker inventory as an auxiliary input to produce speaker labels as well as multi-speaker transcriptions. All model parameters are optimized by speaker-attributed maximum mutual info…
Nara Institute of Science and Technology（奈良先端科学技术大学院大学）；RIKEN（理化学研究所）
In previous work, we developed a closed-loop speech chain model based on deep learning, in which the architecture enabled the automatic speech recognition (ASR) and text-to-speech synthesis (TTS) components to mutually improve their performance. This was accomplished by the two parts teaching each other using both labeled and unlabeled data. This approach could significantly improve model performance within a single-speaker speech dataset, but only a slight increase could be gained in multi-speaker tasks. Furthermore, the model is still unable to handle unseen speakers. In this paper, we prese…
We propose speaker separation using speaker inventories and estimated speech (SSUSIES), a framework leveraging speaker profiles and estimated speech for speaker separation. SSUSIES contains two methods, speaker separation using speaker inventories (SSUSI) and speaker separation using estimated speech (SSUES). SSUSI performs speaker separation with the help of speaker inventory. By combining the advantages of permutation invariant training (PIT) and speech extraction, SSUSI significantly outperforms conventional approaches. SSUES is a widely applicable technique that can substantially improve s…
We describe a neural network-based system for text-to-speech (TTS) synthesis that is able to generate speech audio in the voice of many different speakers, including those unseen during training. Our system consists of three independently trained components: (1) a speaker encoder network, trained on a speaker verification task using an independent dataset of noisy speech from thousands of speakers without transcripts, to generate a fixed-dimensional embedding vector from seconds of reference speech from a target speaker; (2) a sequence-to-sequence synthesis network based on Tacotron 2, which g…
Training a multi-speaker Text-to-Speech (TTS) model from scratch is computationally expensive and adding new speakers to the dataset requires the model to be re-trained. The naive solution of sequential fine-tuning of a model for new speakers can lead to poor performance of older speakers. This phenomenon is known as catastrophic forgetting. In this paper, we look at TTS modeling from a continual learning perspective, where the goal is to add new speakers without forgetting previous speakers. Therefore, we first propose an experimental setup and show that serial fine-tuning for new speakers ca…
In this paper, a novel architecture for speaker recognition is proposed by cascading speech enhancement and speaker processing. Its aim is to improve speaker recognition performance when speech signals are corrupted by noise. Instead of individually processing speech enhancement and speaker recognition, the two modules are integrated into one framework by a joint optimisation using deep neural networks. Furthermore, to increase robustness against noise, a multi-stage attention mechanism is employed to highlight the speaker related features learned from context information in time and frequency…
NTT Communication Science Laboratories, NTT Corporation（日本电信电话株式会社NTT通信科学实验室）；Brno University of Technology（布尔诺理工大学）
Target speech extraction, which extracts a single target source in a mixture given clues about the target speaker, has attracted increasing attention. We have recently proposed SpeakerBeam, which exploits an adaptation utterance of the target speaker to extract his/her voice characteristics that are then used to guide a neural network towards extracting speech of that speaker. SpeakerBeam presents a practical alternative to speech separation as it enables tracking speech of a target speaker across utterances, and achieves promising speech extraction performance. However, it sometimes fails whe…
Fine-tuning is a popular method for adapting text-to-speech (TTS) models to new speakers. However this approach has some challenges. Usually fine-tuning requires several hours of high quality speech per speaker. There is also that fine-tuning will negatively affect the quality of speech synthesis for previously learnt speakers. In this paper we propose an alternative approach for TTS adaptation based on using parameter-efficient adapter modules. In the proposed approach, a few small adapter modules are added to the original network. The original weights are frozen, and only the adapters are fi…
Brno University of Technology（布尔诺理工大学）；Sharif DeepMine Ltd.（谢里夫DeepMine有限公司）
DeepMine is a speech database in Persian and English designed to build and evaluate text-dependent, text-prompted, and text-independent speaker verification, as well as Persian speech recognition systems. It contains more than 1850 speakers and 540 thousand recordings overall, more than 480 hours of speech are transcribed. It is the first public large-scale speaker verification database in Persian, the largest public text-dependent and text-prompted speaker verification database in English, and the largest public evaluation dataset for text-independent speaker verification. It has a good cover…
Worcester Polytechnic Institute (WPI)（伍斯特理工学院（WPI））
We propose a new method for speaker diarization that can handle overlapping speech with 2+ people. Our method is based on compositional embeddings [1]: Like standard speaker embedding methods such as x-vector [2], compositional embedding models contain a function f that separates speech from different speakers. In addition, they include a composition function g to compute set-union operations in the embedding space so as to infer the set of speakers within the input audio. In an experiment on multi-person speaker identification using synthesized LibriSpeech data, the proposed method outperform…
In this paper, we propose a novel auxiliary loss function for target-speaker automatic speech recognition (ASR). Our method automatically extracts and transcribes target speaker's utterances from a monaural mixture of multiple speakers speech given a short sample of the target speaker. The proposed auxiliary loss function attempts to additionally maximize interference speaker ASR accuracy during training. This will regularize the network to achieve a better representation for speaker separation, thus achieving better accuracy on the target-speaker ASR. We evaluated our proposed method using tw…
The vast majority of speech separation methods assume that the number of speakers is known in advance, hence they are specific to the number of speakers. By contrast, a more realistic and challenging task is to separate a mixture in which the number of speakers is unknown. This paper formulates the speech separation with the unknown number of speakers as a multi-pass source extraction problem and proposes a coarse-to-fine recursive speech separation method. This method comprises two stages, namely, recursive cue extraction and target speaker extraction. The recursive cue extraction stage deter…
This paper investigates the use of target-speaker automatic speech recognition (TS-ASR) for simultaneous speech recognition and speaker diarization of single-channel dialogue recordings. TS-ASR is a technique to automatically extract and recognize only the speech of a target speaker given a short sample utterance of that speaker. One obvious drawback of TS-ASR is that it cannot be used when the speakers in the recordings are unknown because it requires a sample of the target speakers in advance of decoding. To remove this limitation, we propose an iterative method, in which (i) the estimation …
In recent years, Text-To-Speech (TTS) has been used as a data augmentation technique for speech recognition to help complement inadequacies in the training data. Correspondingly, we investigate the use of a multi-speaker TTS system to synthesize speech in support of speaker recognition. In this study we focus the analysis on tasks where a relatively small number of speakers is available for training. We observe on our datasets that TTS synthesized speech improves cross-domain speaker recognition performance and can be combined effectively with multi-style training. Additionally, we explore the…
University of Augsburg（奥格斯堡大学）；Imperial College London（帝国理工学院）
We present a novel source separation model to decompose asingle-channel speech signal into two speech segments belonging to two different speakers. The proposed model is a neural network based on residual blocks, and uses learnt speaker embeddings created from additional clean context recordings of the two speakers as input to assist in attributing the different time-frequency bins to the two speakers. In experiments, we show that the proposed model yields good performance in the source separation task, and outperforms the state-of-the-art baselines. Specifically, separating speech from the ch…
University of Sheffield（谢菲尔德大学）；Toshiba Cambridge Research Laboratory（东芝剑桥研究实验室）
In this paper, we present a novel multi-channel speech extraction system to simultaneously extract multiple clean individual sources from a mixture in noisy and reverberant environments. The proposed method is built on an improved multi-channel time-domain speech separation network which employs speaker embeddings to identify and extract multiple targets without label permutation ambiguity. To efficiently inform the speaker information to the extraction model, we propose a new speaker conditioning mechanism by designing an additional speaker branch for receiving external speaker embeddings. Ex…
Creating universal speaker encoders which are robust for different acoustic and speech duration conditions is a big challenge today. According to our observations systems trained on short speech segments are optimal for short phrase speaker verification and systems trained on long segments are superior for long segments verification. A system trained simultaneously on pooled short and long speech segments does not give optimal verification results and usually degrades both for short and long segments. This paper addresses the problem of creating universal speaker encoders for different speech …
Human-Computer Communications Laboratory（人机通信实验室）；The Chinese University of Hong Kong（香港中文大学）；SpeechX Limited（SpeechX有限公司）；University of Cambridge（剑桥大学）
Though significant progress has been made for the voice conversion (VC) of typical speech, VC for atypical speech, e.g., dysarthric and second-language (L2) speech, remains a challenge, since it involves correcting for atypical prosody while maintaining speaker identity. To address this issue, we propose a VC system with explicit prosodic modelling and deep speaker embedding (DSE) learning. First, a speech-encoder strives to extract robust phoneme embeddings from atypical speech. Second, a prosody corrector takes in phoneme embeddings to infer typical phoneme duration and pitch values. Third, …
Università degli Studi di Torino（都灵大学）；Cerence Inc.（赛轮思公司）
Deep learning models are becoming predominant in many fields of machine learning. Text-to-Speech (TTS), the process of synthesizing artificial speech from text, is no exception. To this end, a deep neural network is usually trained using a corpus of several hours of recorded speech from a single speaker. Trying to produce the voice of a speaker other than the one learned is expensive and requires large effort since it is necessary to record a new dataset and retrain the model. This is the main reason why the TTS models are usually single speaker. The proposed approach has the goal to overcome …
Analysis of Speech Temporal Dynamics in the Context of Speaker Verification and Voice Anonymization
Université de Lorraine, CNRS, Inria Loria（卢瓦尔大学、法国国家科学研究中心、Inria Loria）；Université de Lille, CNRS, Inria Centrale Lille, UMR 9189 - CRIStAL Lille（里尔大学、法国国家科学研究中心、Inria Centrale Lille、UMR 9189 - CRIStAL Lille）
Recently, the research on ad-hoc microphone arrays with deep learning has drawn much attention, especially in speech enhancement and separation. Because an ad-hoc microphone array may cover such a large area that multiple speakers may locate far apart and talk independently, target-dependent speech separation, which aims to extract a target speaker from a mixed speech, is important for extracting and tracing a specific speaker in the ad-hoc array. However, this technique has not been explored yet. In this paper, we propose deep ad-hoc beamforming based on speaker extraction, which is to our kn…
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Kwai（快手）
Recently, end-to-end (E2E) models become a competitive alternative to the conventional hybrid automatic speech recognition (ASR) systems. However, they still suffer from speaker mismatch in training and testing condition. In this paper, we use Speech-Transformer (ST) as the study platform to investigate speaker aware training of E2E models. We propose a model called Speaker-Aware Speech-Transformer (SAST), which is a standard ST equipped with a speaker attention module (SAM). The SAM has a static speaker knowledge block (SKB) that is made of i-vectors. At each time step, the encoder output att…
National University of Singapore（新加坡国立大学）；The Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Bremen（不来梅大学）
Speaker extraction seeks to extract the clean speech of a target speaker from a multi-talker mixture speech. There have been studies to use a pre-recorded speech sample or face image of the target speaker as the speaker cue. In human communication, co-speech gestures that are naturally timed with speech also contribute to speech perception. In this work, we explore the use of co-speech gestures sequence, e.g. hand and body movements, as the speaker cue for speaker extraction, which could be easily obtained from low-resolution video recordings, thus more available than face recordings. We propo…
Nanyang Technological University（南洋理工大学）；National University of Singapore（新加坡国立大学）；University of Bremen（不来梅大学）；Kriston AI Lab（Kriston AI实验室）
Speaker extraction aims to mimic humans' selective auditory attention by extracting a target speaker's voice from a multi-talker environment. It is common to perform the extraction in frequency-domain, and reconstruct the time-domain signal from the extracted magnitude and estimated phase spectra. However, such an approach is adversely affected by the inherent difficulty of phase estimation. Inspired by Conv-TasNet, we propose a time-domain speaker extraction network (SpEx) that converts the mixture speech into multi-scale embedding coefficients instead of decomposing the speech signal into ma…
Speech recognition in cocktail-party environments remains a significant challenge for state-of-the-art speech recognition systems, as it is extremely difficult to extract an acoustic signal of an individual speaker from a background of overlapping speech with similar frequency and temporal characteristics. We propose the use of speaker-targeted acoustic and audio-visual models for this task. We complement the acoustic features in a hybrid DNN-HMM model with information of the target speaker's identity as well as visual features from the mouth region of the target speaker. Experimentation was p…
Binaural speech separation in real-world scenarios often involves moving speakers. Most current speech separation methods use utterance-level permutation invariant training (u-PIT) for training. In inference time, however, the order of outputs can be inconsistent over time particularly in long-form speech separation. This situation which is referred to as the speaker swap problem is even more problematic when speakers constantly move in space and therefore poses a challenge for consistent placement of speakers in output channels. Here, we describe a real-time binaural speech separation model b…
Carnegie Mellon University（卡内基梅隆大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper, we present a novel framework that jointly performs three tasks: speaker diarization, speech separation, and speaker counting. Our proposed framework integrates speaker diarization based on end-to-end neural diarization (EEND) models, speaker counting with encoder-decoder based attractors (EDA), and speech separation using Conv-TasNet. In addition, we propose a multiple 1x1 convolutional layer architecture for estimating the separation masks corresponding to a flexible number of speakers and a fusion technique for refining the separated speech signal with obtained speaker diariza…
Indian Institute of Technology Guwahati（印度理工学院古瓦哈提分校）；National University of Singapore（新加坡国立大学）
Emotional state of a speaker is found to have significant effect in speech production, which can deviate speech from that arising from neutral state. This makes identifying speakers with different emotions a challenging task as generally the speaker models are trained using neutral speech. In this work, we propose to overcome this problem by creation of emotion invariant speaker embedding. We learn an extractor network that maps the test embeddings with different emotions obtained using i-vector based system to an emotion invariant space. The resultant test embeddings thus become emotion invar…
Conversational speech not only contains several variants of neutral speech but is also prominently interlaced with several speaker generated non-speech sounds such as laughter and breath. A robust speaker recognition system should be capable of recognizing a speaker irrespective of these variations in his speech. An understanding of whether the speaker-specific information represented by these variations is similar or not helps build a good speaker recognition system. In this paper, speaker variations captured by neutral speech of a speaker is analyzed by considering speech-laugh (a variant of…
Speech self-supervised models such as wav2vec 2.0 and HuBERT are making revolutionary progress in Automatic Speech Recognition (ASR). However, they have not been totally proven to produce better performance on tasks other than ASR. In this work, we explored partial fine-tuning and entire fine-tuning on wav2vec 2.0 and HuBERT pre-trained models for three non-ASR speech tasks: Speech Emotion Recognition, Speaker Verification and Spoken Language Understanding. With simple proposed downstream frameworks, the best scores reached 79.58% weighted accuracy on speaker-dependent setting and 73.01% weigh…
Tel Aviv University（特拉维夫大学）；Facebook AI Research（Facebook人工智能研究院）
Single channel speech separation has experienced great progress in the last few years. However, training neural speech separation for a large number of speakers (e.g., more than 10 speakers) is out of reach for the current methods, which rely on the Permutation Invariant Loss (PIT). In this work, we present a permutation invariant training that employs the Hungarian algorithm in order to train with an $O(C^3)$ time complexity, where $C$ is the number of speakers, in comparison to $O(C!)$ of PIT based methods. Furthermore, we present a modified architecture that can handle the increased number …
National University of Singapore（新加坡国立大学）；Nanyang Technological University（南洋理工大学）
The performance of speaker verification degrades significantly when the test speech is corrupted by interference speakers. Speaker diarization does well to separate speakers if the speakers are temporally overlapped. However, if multi-talkers speak at the same time, we need the technique to separate the speech in the spectral domain. This paper proposes an overlapped multi-talker speaker verification framework by using target speaker extraction methods. Specifically, given the target speaker information, the target speaker's speech is firstly extracted from the overlapped multi-talker speech b…
Mitsubishi Electric Research Laboratories (MERL)（三菱电机研究实验室）；The Ohio State University（俄亥俄州立大学）
This study investigates robust speaker localization for con-tinuous speech separation and speaker diarization, where we use speaker directions to group non-contiguous segments of the same speaker. Assuming that speakers do not move and are located in different directions, the direction of arrival (DOA) information provides an informative cue for accurate sequential grouping and speaker diarization. Our system is block-online in the following sense. Given a block of frames with at most two speakers, we apply a two-speaker separa-tion model to separate (and enhance) the speakers, estimate the DO…
Institute of Automation, Chinese Academy of Sciences (CASIA)（中国科学院自动化研究所）；Johns Hopkins University（约翰斯·霍普金斯大学）
Speech separation has been extensively explored to tackle the cocktail party problem. However, these studies are still far from having enough generalization capabilities for real scenarios. In this work, we raise a common strategy named Speaker-Conditional Chain Model to process complex speech recordings. In the proposed method, our model first infers the identities of variable numbers of speakers from the observation based on a sequence-to-sequence model. Then, it takes the information from the inferred speakers as conditions to extract their speech sources. With the predicted speaker informa…
College of Computer Science, Inner Mongolia University（内蒙古大学计算机学院）
Deep learning has shown a great potential for speech separation, especially for speech and non-speech separation. However, it encounters permutation problem for multi-speaker separation where both target and interference are speech. Permutation Invariant training (PIT) was proposed to solve this problem by permuting the order of the multiple speakers. Another way is to use an anchor speech, a short speech of the target speaker, to model the speaker identity. In this paper, we propose a simple strategy to train a long short-term memory (LSTM) model to solve the permutation problem in speaker se…
In multi-talker scenarios such as meetings and conversations, speech processing systems are usually required to transcribe the audio as well as identify the speakers for downstream applications. Since overlapped speech is common in this case, conventional approaches usually address this problem in a cascaded fashion that involves speech separation, speech recognition and speaker identification that are trained independently. In this paper, we propose Streaming Unmixing, Recognition and Identification Transducer (SURIT) -- a new framework that deals with this problem in an end-to-end streaming …
In this paper we propose a method of single-channel speaker-independent multi-speaker speech separation for an unknown number of speakers. As opposed to previous works, in which the number of speakers is assumed to be known in advance and speech separation models are specific for the number of speakers, our proposed method can be applied to cases with different numbers of speakers using a single model by recursively separating a speaker. To make the separation model recursively applicable, we propose one-and-rest permutation invariant training (OR-PIT). Evaluation on WSJ0-2mix and WSJ0-3mix da…
Many approaches can derive information about a single speaker's identity from the speech by learning to recognize consistent characteristics of acoustic parameters. However, it is challenging to determine identity information when there are multiple concurrent speakers in a given signal. In this paper, we propose a novel deep speaker representation strategy that can reliably extract multiple speaker identities from an overlapped speech. We design a network that can extract a high-level embedding that contains information about each speaker's identity from a given mixture. Unlike conventional a…
In this paper, a new speech feature fusion method is proposed for speaker recognition on the basis of the cross gate parallel convolutional neural network (CG-PCNN). The Mel filter bank features (MFBFs) of different frequency resolutions can be extracted from each speech frame of a speaker's speech by several Mel filter banks, where the numbers of the triangular filters in the Mel filter banks are different. Due to the frequency resolutions of these MFBFs are different, there are some complementaries for these MFBFs. The CG-PCNN is utilized to extract the deep features from these MFBFs, which …
National University of Singapore（新加坡国立大学）；Tencent Ethereal Audio Lab（腾讯天籁音频实验室）
Speaker verification has been studied mostly under the single-talker condition. It is adversely affected in the presence of interference speakers. Inspired by the study on target speaker extraction, e.g., SpEx, we propose a unified speaker verification framework for both single- and multi-talker speech, that is able to pay selective auditory attention to the target speaker. This target speaker verification (tSV) framework jointly optimizes a speaker attention module and a speaker representation module via multi-task learning. We study four different target speaker embedding schemes under the t…
In recent years identity-vector (i-vector) based speaker verification (SV) systems have become very successful. Nevertheless, environmental noise and speech duration variability still have a significant effect on degrading the performance of these systems. In many real-life applications, duration of recordings are very short; as a result, extracted i-vectors cannot reliably represent the attributes of the speaker. Here, we investigate the effect of speech duration on the performance of three state-of-the-art speaker recognition systems. In addition, using a variety of available score fusion me…
Khalifa University（哈利法大学）；Mohammed VI Polytechnic University（穆罕默德六世理工大学）；University of Sharjah（沙迦大学）
Speech signals are subjected to more acoustic interference and emotional factors than other signals. Noisy emotion-riddled speech data is a challenge for real-time speech processing applications. It is essential to find an effective way to segregate the dominant signal from other external influences. An ideal system should have the capacity to accurately recognize required auditory events from a complex scene taken in an unfavorable situation. This paper proposes a novel approach to speaker identification in unfavorable conditions such as emotion and interference using a pre-trained Deep Neura…
Usable speech criteria are proposed to extract minimally corrupted speech for speaker identification (SID) in co-channel speech. In co-channel speech, either speaker can randomly appear as the stronger speaker or the weaker one at a time. Hence, the extracted usable segments are separated in time and need to be organized into speaker streams for SID. In this paper, we focus to organize extracted usable speech segment into a single stream for the same speaker by speaker assignment system. For this, we develop model-based speaker assignment method based on posterior probability and exhaustive se…
Northwestern Polytechnical University（西北工业大学）；Microsoft Corporation（微软公司）；Beijing Shell Shell Technology Co., Ltd.（北京贝壳科技有限公司）；University of Science and Technology of China（中国科学技术大学）
In this paper, we present AISHELL-4, a sizable real-recorded Mandarin speech dataset collected by 8-channel circular microphone array for speech processing in conference scenario. The dataset consists of 211 recorded meeting sessions, each containing 4 to 8 speakers, with a total length of 120 hours. This dataset aims to bridge the advanced research on multi-speaker processing and the practical application scenario in three aspects. With real recorded meetings, AISHELL-4 provides realistic acoustics and rich natural speech characteristics in conversation such as short pause, speech overlap, qu…
Seoul National University（首尔国立大学）；Samsung Research, Samsung Electronics（三星电子三星研究院）
Training a text-to-speech (TTS) model requires a large scale text labeled speech corpus, which is troublesome to collect. In this paper, we propose a transfer learning framework for TTS that utilizes a large amount of unlabeled speech dataset for pre-training. By leveraging wav2vec2.0 representation, unlabeled speech can highly improve performance, especially in the lack of labeled speech. We also extend the proposed method to zero-shot multi-speaker TTS (ZS-TTS). The experimental results verify the effectiveness of the proposed method in terms of naturalness, intelligibility, and speaker gene…
