我们提出了 mixture to mixture（M2M）训练，这是一种弱监督神经语音分离算法，利用近讲混合信号作为弱监督来训练判别式模型，以分离远场混合信号。我们的思路是，对于目标说话人，其近讲混合信号具有比任何远场混合信号高得多的目标说话人信噪比（SNR），因此可用于设计分离任务的弱监督。为实现这一点，在每个训练步骤中，我们将远场混合信号输入深度神经网络（DNN），为每个说话人生成中间估计；并且对于所考虑的每个近讲和远场麦克风，我们对 DNN 估计进行线性滤波，并优化一项损失，使所有说话人的滤波后估计之和等于每个所考虑麦克风采集到的混合信号。在模拟混响条件下的双人说话分离任务上的评估结果表明，M2M 能够有效利用近讲混合信号作为弱监督来分离远场混合信号。
英文摘要：
We propose mixture to mixture (M2M) training, a weakly-supervised neural speech separation algorithm that leverages close-talk mixtures as a weak supervision for training discriminative models to separate far-field mixtures. Our idea is that, for a target speaker, its close-talk mixture has a much higher signal-to-noise ratio (SNR) of the target speaker than any far-field mixtures, and hence could be utilized to design a weak supervision for separation. To realize this, at each training step we feed a far-field mixture to a deep neural network (DNN) to produce an intermediate estimate for each speaker, and, for each of considered close-talk and far-field microphones, we linearly filter the DNN estimates and optimize a loss so that the filtered estimates of all the speakers can sum up to the mixture captured by each of the considered microphones. Evaluation results on a 2-speaker separation task in simulated reverberant conditions show that M2M can effectively leverage close-talk mixtures as a weak supervision for separating far-field mixtures.
Southern University of Science and Technology（南方科技大学）；Meta Reality Labs Research（Meta现实实验室）；Carnegie Mellon University（卡内基梅隆大学）
While far-field multi-talker mixtures are recorded, each speaker can wear a close-talk microphone so that close-talk mixtures can be recorded at the same time. Although each close-talk mixture has a high signal-to-noise ratio (SNR) of the wearer, it has a very limited range of applications, as it also contains significant cross-talk speech by other speakers and is not clean enough. In this context, we propose a novel task named cross-talk reduction (CTR) which aims at reducing cross-talk speech, and a novel solution named CTRnet which is based on unsupervised or weakly-supervised neural speech…
In this paper, we propose a dual-encoder ASR architecture for joint modeling of close-talk (CT) and far-talk (FT) speech, in order to combine the advantages of CT and FT devices for better accuracy. The key idea is to add an encoder selection network to choose the optimal input source (CT or FT) and the corresponding encoder. We use a single-channel encoder for CT speech and a multi-channel encoder with Spatial Filtering neural beamforming for FT speech, which are jointly trained with the encoder selection. We validate our approach on both attention-based and RNN Transducer end-to-end ASR syst…
Columbia University（哥伦比亚大学）；Shanghai Jiao Tong University（上海交通大学）；Microsoft Corporation（微软公司）；NTT Corporation（日本电报电话公司）；Johns Hopkins University（约翰斯·霍普金斯大学）；Google Research（谷歌研究院）
Leveraging additional speaker information to facilitate speech separation has received increasing attention in recent years. Recent research includes extracting target speech by using the target speaker's voice snippet and jointly separating all participating speakers by using a pool of additional speaker signals, which is known as speech separation using speaker inventory (SSUSI). However, all these systems ideally assume that the pre-enrolled speaker signals are available and are only evaluated on simple data configurations. In realistic multi-talker conversations, the speech signal contains…
To improve speaker verification in real scenarios with interference speakers, noise, and reverberation, we propose to bring together advancements made in multi-channel speech features. Specifically, we combine spectral, spatial, and directional features, which includes inter-channel phase difference, multi-channel sinc convolutions, directional power ratio features, and angle features. To maximally leverage supervised learning, our framework is also equipped with multi-channel speech enhancement and voice activity detection. On all simulated, replayed, and real recordings, we observe large and…
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…
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…
Cross-Talk Speech Reduction, by Separation, for Separation
Department of Computer Science and Engineering（计算机科学与工程系）；Southern University of Science and Technology（南方科技大学）；Language Technologies Institute（语言技术研究所）；Carnegie Mellon University（卡内基梅隆大学）
Shanghai Jiao Tong University（上海交通大学）；Tencent AI Lab（腾讯人工智能实验室）
Although great progresses have been made in automatic speech recognition (ASR), significant performance degradation is still observed when recognizing multi-talker mixed speech. In this paper, we propose and evaluate several architectures to address this problem under the assumption that only a single channel of mixed signal is available. Our technique extends permutation invariant training (PIT) by introducing the front-end feature separation module with the minimum mean square error (MSE) criterion and the back-end recognition module with the minimum cross entropy (CE) criterion. More specif…
University of Kentucky（肯塔基大学）；University of Connecticut（康涅狄格大学）；Marquette University（马凯特大学）
Dysarthria is a motor speech disorder often characterized by reduced speech intelligibility through slow, uncoordinated control of speech production muscles. Automatic Speech recognition (ASR) systems may help dysarthric talkers communicate more effectively. To have robust dysarthria-specific ASR, sufficient training speech is required, which is not readily available. Recent advances in Text-To-Speech (TTS) synthesis multi-speaker end-to-end TTS systems suggest the possibility of using synthesis for data augmentation. In this paper, we aim to improve multi-speaker end-to-end TTS systems to syn…
In this letter, we present a novel multi-talker minimum variance distortionless response (MVDR) beamforming as the front-end of an automatic speech recognition (ASR) system in a dinner party scenario. The CHiME-5 dataset is selected to evaluate our proposal for overlapping multi-talker scenario with severe noise. A detailed study on beamforming is conducted based on the proposed extended complex Gaussian mixture model (CGMM) integrated with various speech separation and speech enhancement masks. Three main changes are made to adopt the original CGMM-based MVDR for the multi-talker scenario. Fi…
Self-supervised learning (SSL) methods which learn representations of data without explicit supervision have gained popularity in speech-processing tasks, particularly for single-talker applications. However, these models often have degraded performance for multi-talker scenarios -- possibly due to the domain mismatch -- which severely limits their use for such applications. In this paper, we investigate the adaptation of upstream SSL models to the multi-talker automatic speech recognition (ASR) task under two conditions. First, when segmented utterances are given, we show that adding a target…
Brno University of Technology（布尔诺理工大学）；NTT Corporation（日本电信电话株式会社）
In typical multi-talker speech recognition systems, a neural network-based acoustic model predicts senone state posteriors for each speaker. These are later used by a single-talker decoder which is applied on each speaker-specific output stream separately. In this work, we argue that such a scheme is sub-optimal and propose a principled solution that decodes all speakers jointly. We modify the acoustic model to predict joint state posteriors for all speakers, enabling the network to express uncertainty about the attribution of parts of the speech signal to the speakers. We employ a joint decod…
Microsoft Research（微软研究院）；Aalborg University（奥尔堡大学）
We propose a novel deep learning model, which supports permutation invariant training (PIT), for speaker independent multi-talker speech separation, commonly known as the cocktail-party problem. Different from most of the prior arts that treat speech separation as a multi-class regression problem and the deep clustering technique that considers it a segmentation (or clustering) problem, our model optimizes for the separation regression error, ignoring the order of mixing sources. This strategy cleverly solves the long-lasting label permutation problem that has prevented progress on deep learni…
Naver Corporation（Naver公司）；University of Oxford（牛津大学）
The objective of this work is speaker diarisation of speech recordings 'in the wild'. The ability to determine speech segments is a crucial part of diarisation systems, accounting for a large proportion of errors. In this paper, we present a simple but effective solution for speech activity detection based on the speaker embeddings. In particular, we discover that the norm of the speaker embedding is an extremely effective indicator of speech activity. The method does not require an independent model for speech activity detection, therefore allows speaker diarisation to be performed using a un…
Generating 3D speech-driven talking head has received more and more attention in recent years. Recent approaches mainly have following limitations: 1) most speaker-independent methods need handcrafted features that are time-consuming to design or unreliable; 2) there is no convincing method to support multilingual or mixlingual speech as input. In this work, we propose a novel approach using phonetic posteriorgrams (PPG). In this way, our method doesn't need hand-crafted features and is more robust to noise compared to recent approaches. Furthermore, our method can support multilingual speech …
Most approaches to multi-talker overlapped speech separation and recognition assume that the number of simultaneously active speakers is given, but in realistic situations, it is typically unknown. To cope with this, we extend an iterative speech extraction system with mechanisms to count the number of sources and combine it with a single-talker speech recognizer to form the first end-to-end multi-talker automatic speech recognition system for an unknown number of active speakers. Our experiments show very promising performance in counting accuracy, source separation and speech recognition on …
See the Speaker: Crafting High-Resolution Talking Faces from Speech with Prior Guidance and Region Refinement
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Speech and Acoustic Laboratory, Joy Future Academy, Jingdong Corporation（语音与声学实验室、Joy Future Academy、京东公司）；Aarhus University（阿arhus大学）
Aalborg University（奥尔堡大学）；Tencent AI Lab（腾讯人工智能实验室）；Microsoft Research（微软研究院）；Oticon A/S（奥迪康公司）
In this paper we propose the utterance-level Permutation Invariant Training (uPIT) technique. uPIT is a practically applicable, end-to-end, deep learning based solution for speaker independent multi-talker speech separation. Specifically, uPIT extends the recently proposed Permutation Invariant Training (PIT) technique with an utterance-level cost function, hence eliminating the need for solving an additional permutation problem during inference, which is otherwise required by frame-level PIT. We achieve this using Recurrent Neural Networks (RNNs) that, during training, minimize the utterance-…
Microsoft Research（微软研究院）；Shanghai Jiao Tong University（上海交通大学）
In this paper, we propose a novel technique for direct recognition of multiple speech streams given the single channel of mixed speech, without first separating them. Our technique is based on permutation invariant training (PIT) for automatic speech recognition (ASR). In PIT-ASR, we compute the average cross entropy (CE) over all frames in the whole utterance for each possible output-target assignment, pick the one with the minimum CE, and optimize for that assignment. PIT-ASR forces all the frames of the same speaker to be aligned with the same output layer. This strategy elegantly solves th…
Neural Text to Articulate Talk: Deep Text to Audiovisual Speech Synthesis achieving both Auditory and Photo-realism
National Technical University of Athens（雅典国家技术大学）；Athena Research Center（雅典娜研究中心）；Foundation for Research & Technology - Hellas (FORTH)（希腊研究与技术基金会（FORTH））
One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A smart assistant needs to determine which voice to recognize and which to ignore and it needs to do so in a streaming, low-latency manner. This work presents two multi-microphone speech enhancement algorithms targeted at this scenario. Targeting on-device use-cases, we assume that the algorithm has access to the signal before the hotword, which is referred to as the noise context. First is the Context Aware Beamformer…
Aalborg University（奥尔堡大学）；Tencent AI Lab（腾讯人工智能实验室）
In this paper we propose to use utterance-level Permutation Invariant Training (uPIT) for speaker independent multi-talker speech separation and denoising, simultaneously. Specifically, we train deep bi-directional Long Short-Term Memory (LSTM) Recurrent Neural Networks (RNNs) using uPIT, for single-channel speaker independent multi-talker speech separation in multiple noisy conditions, including both synthetic and real-life noise signals. We focus our experiments on generalizability and noise robustness of models that rely on various types of a priori knowledge e.g. in terms of noise type and…
Sony Corporation（索尼公司）；Carnegie Mellon University（卡内基梅隆大学）
Although end-to-end automatic speech recognition (E2E ASR) has achieved great performance in tasks that have numerous paired data, it is still challenging to make E2E ASR robust against noisy and low-resource conditions. In this study, we investigated data augmentation methods for E2E ASR in distant-talk scenarios. E2E ASR models are trained on the series of CHiME challenge datasets, which are suitable tasks for studying robustness against noisy and spontaneous speech. We propose to use three augmentation methods and thier combinations: 1) data augmentation using text-to-speech (TTS) data, 2) …
The goal of this work is to reconstruct speech from a silent talking face video. Recent studies have shown impressive performance on synthesizing speech from silent talking face videos. However, they have not explicitly considered on varying identity characteristics of different speakers, which place a challenge in the video-to-speech synthesis, and this becomes more critical in unseen-speaker settings. Our approach is to separate the speech content and the visage-style from a given silent talking face video. By guiding the model to independently focus on modeling the two representations, we c…
Recent adoption of deep learning methods to the field of machine lipreading research gives us two options to pursue to improve system performance. Either, we develop end-to-end systems holistically or, we experiment to further our understanding of the visual speech signal. The latter option is more difficult but this knowledge would enable researchers to both improve systems and apply the new knowledge to other domains such as speech therapy. One challenge in lipreading systems is the correct labeling of the classifiers. These labels map an estimated function between visemes on the lips and th…
Recent work has shown that speech paired with images can be used to learn semantically meaningful speech representations even without any textual supervision. In real-world low-resource settings, however, we often have access to some transcribed speech. We study whether and how visual grounding is useful in the presence of varying amounts of textual supervision. In particular, we consider the task of semantic speech retrieval in a low-resource setting. We use a previously studied data set and task, where models are trained on images with spoken captions and evaluated on human judgments of sema…
Tsinghua University（清华大学）；University of Chinese Academy of Sciences（中国科学院大学）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；North China Power Engineering CO., LTD. of China Power Engineering Consulting Group（中国电力工程顾问集团华北电力设计院有限公司）
Utterance-level permutation invariant training (uPIT) has achieved promising progress on single-channel multi-talker speech separation task. Long short-term memory (LSTM) and bidirectional LSTM (BLSTM) are widely used as the separation networks of uPIT, i.e. uPIT-LSTM and uPIT-BLSTM. uPIT-LSTM has lower latency but worse performance, while uPIT-BLSTM has better performance but higher latency. In this paper, we propose using latency-controlled BLSTM (LC-BLSTM) during inference to fulfill low-latency and good-performance speech separation. To find a better training strategy for BLSTM-based separ…
NTT Media Intelligence Laboratories, NTT Corporation（日本电信电话株式会社媒体智能研究所）；Nagaoka University of Technology（长冈技术科学大学）
In this paper, we present a novel modeling method for single-channel multi-talker overlapped automatic speech recognition (ASR) systems. Fully neural network based end-to-end models have dramatically improved the performance of multi-taker overlapped ASR tasks. One promising approach for end-to-end modeling is autoregressive modeling with serialized output training in which transcriptions of multiple speakers are recursively generated one after another. This enables us to naturally capture relationships between speakers. However, the conventional modeling method cannot explicitly take into acc…
University of Modena and Reggio Emilia（摩德纳-雷焦艾米利亚大学）；Istituto Italiano di Tecnologia（意大利理工学院）
In this paper, we address the problem of enhancing the speech of a speaker of interest in a cocktail party scenario when visual information of the speaker of interest is available. Contrary to most previous studies, we do not learn visual features on the typically small audio-visual datasets, but use an already available face landmark detector (trained on a separate image dataset). The landmarks are used by LSTM-based models to generate time-frequency masks which are applied to the acoustic mixed-speech spectrogram. Results show that: (i) landmark motion features are very effective features fo…
National University of Singapore（新加坡国立大学）；Tianjin University（天津大学）；the Chinese University of Hong Kong, Shenzhen（香港中文大学（深圳））；University of Bremen（不来梅大学）；Kriston AI（Kriston人工智能）
A speaker extraction algorithm seeks to extract the target speaker's speech from a multi-talker speech mixture. The prior studies focus mostly on speaker extraction from a highly overlapped multi-talker speech mixture. However, the target-interference speaker overlapping ratios could vary over a wide range from 0% to 100% in natural speech communication, furthermore, the target speaker could be absent in the speech mixture, the speech mixtures in such universal multi-talker scenarios are described as general speech mixtures. The speaker extraction algorithm requires an auxiliary reference, suc…
Technion -- Israel Institute of Technology（以色列理工学院）
Human subjective evaluation is optimal to assess speech quality for human perception. The recently introduced deep noise suppression mean opinion score (DNSMOS) metric was shown to estimate human ratings with great accuracy. The signal-to-distortion ratio (SDR) metric is widely used to evaluate residual-echo suppression (RES) systems by estimating speech quality during double-talk. However, since the SDR is affected by both speech distortion and residual-echo presence, it does not correlate well with human ratings according to the DNSMOS. To address that, we introduce two objective metrics to …
Speech recognizers trained on close-talking speech do not generalize to distant speech and the word error rate degradation can be as large as 40% absolute. Most studies focus on tackling distant speech recognition as a separate problem, leaving little effort to adapting close-talking speech recognizers to distant speech. In this work, we review several approaches from a domain adaptation perspective. These approaches, including speech enhancement, multi-condition training, data augmentation, and autoencoders, all involve a transformation of the data between domains. We conduct experiments on t…
KAIST（韩国科学技术院）；Mokwon University（木原大学）；KAIST Institute for Artificial Intelligence（韩国科学技术院人工智能研究所）
Many speech enhancement methods try to learn the relationship between noisy and clean speech, obtained using an acoustic room simulator. We point out several limitations of enhancement methods relying on clean speech targets; the goal of this work is proposing an alternative learning algorithm, called acoustic and adversarial supervision (AAS). AAS makes the enhanced output both maximizing the likelihood of transcription on the pre-trained acoustic model and having general characteristics of clean speech, which improve generalization on unseen noisy speeches. We employ the connectionist tempor…
Self-supervised learning has attracted plenty of recent research interest. However, most works for self-supervision in speech are typically unimodal and there has been limited work that studies the interaction between audio and visual modalities for cross-modal self-supervision. This work (1) investigates visual self-supervision via face reconstruction to guide the learning of audio representations; (2) proposes an audio-only self-supervision approach for speech representation learning; (3) shows that a multi-task combination of the proposed visual and audio self-supervision is beneficial for …
This paper presents a novel streaming automatic speech recognition (ASR) framework for multi-talker overlapping speech captured by a distant microphone array with an arbitrary geometry. Our framework, named t-SOT-VA, capitalizes on independently developed two recent technologies; array-geometry-agnostic continuous speech separation, or VarArray, and streaming multi-talker ASR based on token-level serialized output training (t-SOT). To combine the best of both technologies, we newly design a t-SOT-based ASR model that generates a serialized multi-talker transcription based on two separated spee…
University of Sharjah（沙迦大学）；The University of Tokyo（东京大学）
This work aims at intensifying text-independent speaker identification performance in real application situations such as noisy and emotional talking conditions. This is achieved by incorporating two different modules: a Computational Auditory Scene Analysis CASA based pre-processing module for noise reduction and cascaded Gaussian Mixture Model Convolutional Neural Network GMM-CNN classifier for speaker identification followed by emotion recognition. This research proposes and evaluates a novel algorithm to improve the accuracy of speaker identification in emotional and highly-noise susceptib…
