Speech enhancement is a task to improve the intelligibility and perceptual quality of degraded speech signal. Recently, neural networks based methods have been applied to speech enhancement. However, many neural network based methods require noisy and clean speech pairs for training. We propose a speech enhancement framework that can be trained with large-scale weakly labelled AudioSet dataset. Weakly labelled data only contain audio tags of audio clips, but not the onset or offset times of speech. We first apply pretrained audio neural networks (PANNs) to detect anchor segments that contain speech or sound events in audio clips. Then, we randomly mix two detected anchor segments containing speech and sound events as a mixture, and build a conditional source separation network using PANNs predictions as soft conditions for speech enhancement. In inference, we input a noisy speech signal with the one-hot encoding of "Speech" as a condition to the trained system to predict enhanced speech. Our system achieves a PESQ of 2.28 and an SSNR of 8.75 dB on the VoiceBank-DEMAND dataset, outperforming the previous SEGAN system of 2.16 and 7.73 dB respectively.
University of Surrey（萨里大学）；Tencent AI Lab（腾讯人工智能实验室）；Qingdao University of Science and Technology（青岛科技大学）
Audio tagging is the task of predicting the presence or absence of sound classes within an audio clip. Previous work in audio tagging focused on relatively small datasets limited to recognising a small number of sound classes. We investigate audio tagging on AudioSet, which is a dataset consisting of over 2 million audio clips and 527 classes. AudioSet is weakly labelled, in that only the presence or absence of sound classes is known for each clip, while the onset and offset times are unknown. To address the weakly-labelled audio tagging problem, we propose attention neural networks as a way t…
Source separation is the task to separate an audio recording into individual sound sources. Source separation is fundamental for computational auditory scene analysis. Previous work on source separation has focused on separating particular sound classes such as speech and music. Many of previous work require mixture and clean source pairs for training. In this work, we propose a source separation framework trained with weakly labelled data. Weakly labelled data only contains the tags of an audio clip, without the occurrence time of sound events. We first train a sound event detection system wi…
Deep learning based speech denoising still suffers from the challenge of improving perceptual quality of enhanced signals. We introduce a generalized framework called Perceptual Ensemble Regularization Loss (PERL) built on the idea of perceptual losses. Perceptual loss discourages distortion to certain speech properties and we analyze it using six large-scale pre-trained models: speaker classification, acoustic model, speaker embedding, emotion classification, and two self-supervised speech encoders (PASE+, wav2vec 2.0). We first build a strong baseline (w/o PERL) using Conformer Transformer N…
University of Science and Technology of China（中国科学技术大学）；Microsoft Research Asia（微软亚洲研究院）
Time-frequency (T-F) domain masking is a mainstream approach for single-channel speech enhancement. Recently, focuses have been put to phase prediction in addition to amplitude prediction. In this paper, we propose a phase-and-harmonics-aware deep neural network (DNN), named PHASEN, for this task. Unlike previous methods that directly use a complex ideal ratio mask to supervise the DNN learning, we design a two-stream network, where amplitude stream and phase stream are dedicated to amplitude and phase prediction. We discover that the two streams should communicate with each other, and this is…
Peking University（北京大学）；Peng Cheng Laboratory（鹏城实验室）；University of Surrey（萨里大学）
Weakly labelled audio tagging aims to predict the classes of sound events within an audio clip, where the onset and offset times of the sound events are not provided. Previous works have used the multiple instance learning (MIL) framework, and exploited the information of the whole audio clip by MIL pooling functions. However, the detailed information of sound events such as their durations may not be considered under this framework. To address this issue, we propose a novel two-stream framework for audio tagging by exploiting the global and local information of sound events. The global stream…
Center for Music Technology, Georgia Institute of Technology（佐治亚理工学院音乐技术中心）；School of Electrical and Electronic Engineering, Nanyang Technological University（南洋理工大学电气与电子工程学院）；Netflix, Inc.（Netflix公司）
We propose a dataset, AVASpeech-SMAD, to assist speech and music activity detection research. With frame-level music labels, the proposed dataset extends the existing AVASpeech dataset, which originally consists of 45 hours of audio and speech activity labels. To the best of our knowledge, the proposed AVASpeech-SMAD is the first open-source dataset that features strong polyphonic labels for both music and speech. The dataset was manually annotated and verified via an iterative cross-checking process. A simple automatic examination was also implemented to further improve the quality of the lab…
In the recent years end to end (E2E) automatic speech recognition (ASR) systems have achieved promising results given sufficient resources. Even for languages where not a lot of labelled data is available, state of the art E2E ASR systems can be developed by pretraining on huge amounts of high resource languages and finetune on low resource languages. For a lot of low resource languages the current approaches are still challenging, since in many cases labelled data is not available in open domain. In this paper we present an approach to create labelled data for Maithili, Bhojpuri and Dogri by …
Centre for Vision, Speech and Signal Processing, University of Surrey（萨里大学视觉、语音与信号处理中心）；ByteDance AI Lab（字节跳动人工智能实验室）；Qingdao University of Science and Technology（青岛科技大学）
Audio pattern recognition is an important research topic in the machine learning area, and includes several tasks such as audio tagging, acoustic scene classification, music classification, speech emotion classification and sound event detection. Recently, neural networks have been applied to tackle audio pattern recognition problems. However, previous systems are built on specific datasets with limited durations. Recently, in computer vision and natural language processing, systems pretrained on large-scale datasets have generalized well to several tasks. However, there is limited research on…
This paper investigates the influence of different acoustic features, audio-events based features and automatic speech translation based lexical features in complex emotion recognition such as curiosity. Pretrained networks, namely, AudioSet Net, VoxCeleb Net and Deep Speech Net trained extensively for different speech based applications are studied for this objective. Information from deep layers of these networks are considered as descriptors and encoded into feature vectors. Experimental results on the EmoReact dataset consisting of 8 complex emotions show the effectiveness, yielding highes…
Representation learning from unlabeled data has been of major interest in artificial intelligence research. While self-supervised speech representation learning has been popular in the speech research community, very few works have comprehensively analyzed audio representation learning for non-speech audio tasks. In this paper, we propose a self-supervised audio representation learning method and apply it to a variety of downstream non-speech audio tasks. We combine the well-known wav2vec 2.0 framework, which has shown success in self-supervised learning for speech tasks, with parameter-effici…
Audiovisual automatic speech recognition (AV-ASR) aims to improve the robustness of a speech recognition system by incorporating visual information. Training fully supervised multimodal models for this task from scratch, however is limited by the need for large labelled audiovisual datasets (in each downstream domain of interest). We present AVFormer, a simple method for augmenting audio-only models with visual information, at the same time performing lightweight domain adaptation. We do this by (i) injecting visual embeddings into a frozen ASR model using lightweight trainable adaptors. We sh…
The goal of speech emotion recognition (SER) is to identify the emotional aspects of speech. The SER challenge for Brazilian Portuguese speech was proposed with short snippets of Portuguese which are classified as neutral, non-neutral female and non-neutral male according to paralinguistic elements (laughing, crying, etc). This dataset contains about $50$ minutes of Brazilian Portuguese speech. As the dataset leans on the small side, we investigate whether a combination of transfer learning and data augmentation techniques can produce positive results. Thus, by combining a data augmentation te…
Towards hate speech detection in low-resource languages: Comparing ASR to acoustic word embeddings on Wolof and Swahili
Stellenbosch University（斯泰伦博斯大学）；Universitat Pompeu Fabra（庞培法布拉大学）；African Institute for Mathematical Sciences（非洲数学科学研究所）；University of Cape Town（开普敦大学）；VoxCroft Analytics（VoxCroft分析公司）
本文比较低资源语言仇恨言论关键词识别中的 ASR 与多语言 AWE，发现同域小样本 ASR 更优，而真实广播场景下 AWE 更稳健。
Whispering is a ubiquitous mode of communication that humans use daily. Despite this, whispered speech has been poorly served by existing speech technology due to a shortage of resources and processing methodology. To remedy this, this paper provides a processing framework that enables access to large and unique data of high-quality whispered speech. We obtain the data from recordings submitted to online platforms as part of the ASMR media-cultural phenomenon. We describe our processing pipeline and a method for improved whispered activity detection (WAD) in the ASMR data. To efficiently obtai…
Dysarthric speech detection (DSD) systems aim to detect characteristics of the neuromotor disorder from speech. Such systems are particularly susceptible to domain mismatch where the training and testing data come from the source and target domains respectively, but the two domains may differ in terms of speech stimuli, disease etiology, etc. It is hard to acquire labelled data in the target domain, due to high costs of annotating sizeable datasets. This paper makes a first attempt to formulate cross-domain DSD as an unsupervised domain adaptation (UDA) problem. We use labelled source-domain d…
L3S Research Center, Leibniz University Hannover（汉诺威莱布尼茨大学L3S研究中心）；Griffith University（格里菲斯大学）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Speech emotion recognition (SER) is the task of recognising human's emotional states from speech. SER is extremely prevalent in helping dialogue systems to truly understand our emotions and become a trustworthy human conversational partner. Due to the lengthy nature of speech, SER also suffers from the lack of abundant labelled data for powerful models like deep neural networks. Pre-trained complex models on large-scale speech datasets have been successfully applied to SER via transfer learning. However, fine-tuning complex models still requires large memory space and results in low inference …
In this paper, we describe our end-to-end multilingual speech translation system submitted to the IWSLT 2021 evaluation campaign on the Multilingual Speech Translation shared task. Our system is built by leveraging transfer learning across modalities, tasks and languages. First, we leverage general-purpose multilingual modules pretrained with large amounts of unlabelled and labelled data. We further enable knowledge transfer from the text task to the speech task by training two tasks jointly. Finally, our multilingual model is finetuned on speech translation task-specific data to achieve the b…
Indraprastha Institute of Information Technology（英德拉普拉斯塔信息技术研究所）；National Institute of Technology, Kurukshetra（库鲁克舍特拉国立理工学院）；Second Language Testing Inc.（第二语言测试公司）
In this paper, we introduce a collaborative and modern annotation tool for audio and speech: audino. The tool allows annotators to define and describe temporal segmentation in audios. These segments can be labelled and transcribed easily using a dynamically generated form. An admin can centrally control user roles and project assignment through the admin dashboard. The dashboard also enables describing labels and their values. The annotations can easily be exported in JSON format for further analysis. The tool allows audio data and their corresponding annotations to be uploaded and assigned to…
Traditionally, in Audio Recognition pipeline, noise is suppressed by the "frontend", relying on preprocessing techniques such as speech enhancement. However, it is not guaranteed that noise will not cascade into downstream pipelines. To understand the actual influence of noise on the entire audio pipeline, in this paper, we directly investigate the impact of noise on a different types of neural models without the preprocessing step. We measure the recognition performances of 4 different neural network models on the task of environment sound classification under the 3 types of noises: \emph{occ…
University of Southern Queensland（南昆士兰大学）；Information Technology University (ITU)（信息技术大学）；University of the West of England (UWE)（西英格兰大学）
Cross-lingual speech emotion recognition (SER) is a crucial task for many real-world applications. The performance of SER systems is often degraded by the differences in the distributions of training and test data. These differences become more apparent when training and test data belong to different languages, which cause a significant performance gap between the validation and test scores. It is imperative to build more robust models that can fit in practical applications of SER systems. Therefore, in this paper, we propose a Generative Adversarial Network (GAN)-based model for multilingual …
Technical University of Denmark（丹麦技术大学）；Copenhagen University Hospital（哥本哈根大学医院）；Copenhagen University（哥本哈根大学）
Use of speech models for automatic speech processing tasks can improve efficiency in the screening, analysis, diagnosis and treatment in medicine and psychiatry. However, the performance of pre-processing speech tasks like segmentation and diarization can drop considerably on in-the-wild clinical data, specifically when the target dataset comprises of atypical speech. In this paper we study the performance of a pre-trained speech model on a dataset comprising of child-clinician conversations in Danish with respect to the classification threshold. Since we do not have access to sufficient label…
Imperial College London（帝国理工学院）；University of Southampton（南安普顿大学）
Speech recognition systems have improved dramatically over the last few years, however, their performance is significantly degraded for the cases of accented or impaired speech. This work explores domain adversarial neural networks (DANN) for speaker-independent speech recognition on the UAS dataset of dysarthric speech. The classification task on 10 spoken digits is performed using an end-to-end CNN taking raw audio as input. The results are compared to a speaker-adaptive (SA) model as well as speaker-dependent (SD) and multi-task learning models (MTL). The experiments conducted in this paper…
Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no labelled data is available in the target language. The current best approach uses transfer learning: a single supervised multilingual model is trained using labelled data from multiple well-resourced languages and then applied to a target zero-resource language (without fine-tuning). However, it is still unclear how the specific choice of training languages affe…
Modern Automatic Speech Recognition (ASR) technology has evolved to identify the speech spoken by native speakers of a language very well. However, identification of the speech spoken by non-native speakers continues to be a major challenge for it. In this work, we first spell out the key requirements for creating a well-curated database of speech samples in non-native accents for training and testing robust ASR systems. We then introduce AccentDB, one such database that contains samples of 4 Indian-English accents collected by us, and a compilation of samples from 4 native-English, and a metr…
AI4Bharat；Indian Institute of Technology, Madras（印度理工学院马德拉斯分校）；Microsoft（微软）
End-to-end (E2E) models have become the default choice for state-of-the-art speech recognition systems. Such models are trained on large amounts of labelled data, which are often not available for low-resource languages. Techniques such as self-supervised learning and transfer learning hold promise, but have not yet been effective in training accurate models. On the other hand, collecting labelled datasets on a diverse set of domains and speakers is very expensive. In this work, we demonstrate an inexpensive and effective alternative to these approaches by ``mining'' text and audio pairs for I…
Idiap Research Institute（伊迪亚普研究所）；Adobe Research（奥多比研究院）
In this paper, we explore various approaches for semi supervised learning in an end to end automatic speech recognition (ASR) framework. The first step in our approach involves training a seed model on the limited amount of labelled data. Additional unlabelled speech data is employed through a data selection mechanism to obtain the best hypothesized output, further used to retrain the seed model. However, uncertainties of the model may not be well captured with a single hypothesis. As opposed to this technique, we apply a dropout mechanism to capture the uncertainty by obtaining multiple hypot…
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
Recently, neural networks based purely on self-attention, such as the Vision Transformer (ViT), have been shown to outperform deep learning models constructed with convolutional neural networks (CNNs) on various vision tasks, thus extending the success of Transformers, which were originally developed for language processing, to the vision domain. A recent study showed that a similar methodology can also be applied to the audio domain. Specifically, the Audio Spectrogram Transformer (AST) achieves state-of-the-art results on various audio classification benchmarks. However, pure Transformer mod…
USQ（南昆士兰大学）；Data61, CSIRO（澳大利亚联邦科学与工业研究组织数据61中心）；University of Southern Queensland (USQ)（南昆士兰大学）；Queensland University of Technology (QUT)（昆士兰科技大学）；University of New South Wales (UNSW)（新南威尔士大学）；Imperial College London（帝国理工学院）；University of Augsburg（奥格斯堡大学）
Inspite the emerging importance of Speech Emotion Recognition (SER), the state-of-the-art accuracy is quite low and needs improvement to make commercial applications of SER viable. A key underlying reason for the low accuracy is the scarcity of emotion datasets, which is a challenge for developing any robust machine learning model in general. In this paper, we propose a solution to this problem: a multi-task learning framework that uses auxiliary tasks for which data is abundantly available. We show that utilisation of this additional data can improve the primary task of SER for which only lim…
Cross-lingual self-supervised learning has been a growing research topic in the last few years. However, current works only explored the use of audio signals to create representations. In this work, we study cross-lingual self-supervised visual representation learning. We use the recently-proposed Raw Audio-Visual Speech Encoders (RAVEn) framework to pre-train an audio-visual model with unlabelled multilingual data, and then fine-tune the visual model on labelled transcriptions. Our experiments show that: (1) multi-lingual models with more data outperform monolingual ones, but, when keeping th…
Imperial College London（伦敦帝国理工学院）；Facebook London（脸书伦敦）；University of Augsburg（奥格斯堡大学）
The large amount of audiovisual content being shared online today has drawn substantial attention to the prospect of audiovisual self-supervised learning. Recent works have focused on each of these modalities separately, while others have attempted to model both simultaneously in a cross-modal fashion. However, comparatively little attention has been given to leveraging one modality as a training objective to learn from the other. In this work, we propose Learning visual speech Representations from Audio via self-supervision (LiRA). Specifically, we train a ResNet+Conformer model to predict ac…
SAV-SE: Scene-aware Audio-Visual Speech Enhancement with Selective State Space Model
School of Computer and Communication Engineering, University of Science and Technology Beijing（北京科技大学计算机与通信工程学院）；School of Electrical Engineering and Telecommunications, The University of New South Wales（新南威尔士大学电气工程与电信学院）；College of Computing and Data Science, Nanyang Technological University（南洋理工大学计算与数据科学学院）；Center for Language and Speech Processing, Johns Hopkins University（约翰霍普金斯大学语言与语音处理中心）；Guangdong Provincial Key Laboratory of Big Data Computing, The Chinese University of Hong Kong (Shenzhen)（香港中文大学（深圳）广东省大数据计算重点实验室）；Shenzhen Research Institute of Big Data（深圳大数据研究院）
In this paper, we present WenetSpeech, a multi-domain Mandarin corpus consisting of 10000+ hours high-quality labeled speech, 2400+ hours weakly labeled speech, and about 10000 hours unlabeled speech, with 22400+ hours in total. We collect the data from YouTube and Podcast, which covers a variety of speaking styles, scenarios, domains, topics, and noisy conditions. An optical character recognition (OCR) based method is introduced to generate the audio/text segmentation candidates for the YouTube data on its corresponding video captions, while a high-quality ASR transcription system is used to …
MIT Computer Science and Artificial Intelligence Laboratory（麻省理工学院计算机科学与人工智能实验室）
In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels. To better capture long-range global context, a recent trend is to add a self-attention mechanism on top of the CNN, forming a CNN-attention hybrid model. However, it is unclear whether the reliance on a CNN is necessary, and if neural networks purely based on attention are sufficient to obtain good performance in audio classification. In this paper, we answer …
Stellenbosch University（斯泰伦博斯大学）；University of Edinburgh（爱丁堡大学）
Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. Such embeddings can form the basis for speech search, indexing and discovery systems when conventional speech recognition is not possible. In zero-resource settings where unlabelled speech is the only available resource, we need a method that gives robust embeddings on an arbitrary language. Here we explore multilingual transfer: we train a single supervised embedding model on labelled data from multiple well-resourced languages and then apply it to unseen zero-resource languages. We consider thr…
Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to make use of unlabelled unimodal data. On the other side, although the effectiveness of large-scale self-supervised learning is well established in both audio and visual modalities, how to integrate those pre-trained models into a multimodal scenario remains underexplored. In this work, we successfully leverage unimodal self-supervised learning to promote the m…
University of Warwick（华威大学）；Google Research（谷歌研究院）；University of Glasgow（格拉斯哥大学）
Large scale databases with high-quality manual annotations are scarce in audio domain. We thus explore a self-supervised graph approach to learning audio representations from highly limited labelled data. Considering each audio sample as a graph node, we propose a subgraph-based framework with novel self-supervision tasks that can learn effective audio representations. During training, subgraphs are constructed by sampling the entire pool of available training data to exploit the relationship between the labelled and unlabeled audio samples. During inference, we use random edges to alleviate t…
