In single-channel speech enhancement, methods based on full-band spectral features have been widely studied. However, only a few methods pay attention to non-full-band spectral features. In this paper, we explore a knowledge distillation framework based on sub-band spectral mapping for single-channel speech enhancement. Specifically, we divide the full frequency band into multiple sub-bands and pre-train an elite-level sub-band enhancement model (teacher model) for each sub-band. These teacher models are dedicated to processing their own sub-bands. Next, under the teacher models' guidance, we train a general sub-band enhancement model (student model) that works for all sub-bands. Without increasing the number of model parameters and computational complexity, the student model's performance is further improved. To evaluate our proposed method, we conducted a large number of experiments on an open-source data set. The final experimental results show that the guidance from the elite-level teacher models dramatically improves the student model's performance, which exceeds the full-band model by employing fewer parameters.
Learning on a massive amount of speech corpus leads to the recent success of many self-supervised speech models. With knowledge distillation, these models may also benefit from the knowledge encoded by language models that are pre-trained on rich sources of texts. The distillation process, however, is challenging due to the modal disparity between textual and speech embedding spaces. This paper studies metric-based distillation to align the embedding space of text and speech with only a small amount of data without modifying the model structure. Since the semantic and granularity gap between t…
BLSP-KD: Bootstrapping Language-Speech Pre-training via Knowledge Distillation
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；Alibaba Group（阿里巴巴集团）；Machine Intelligence Technology Lab, Alibaba Group（阿里巴巴集团机器智能技术实验室）
National Taiwan University（台湾大学）；ASUS Intelligent Cloud Services（华硕智能云服务）
Distilled self-supervised models have shown competitive performance and efficiency in recent years. However, there is a lack of experience in jointly distilling multiple self-supervised speech models. In our work, we performed Ensemble Knowledge Distillation (EKD) on various self-supervised speech models such as HuBERT, RobustHuBERT, and WavLM. We tried two different aggregation techniques, layerwise-average and layerwise-concatenation, to the representations of different teacher models and found that the former was more effective. On top of that, we proposed a multiple prediction head method …
Monaural speech enhancement (SE) provides a versatile and cost-effective approach to SE tasks by utilizing recordings from a single microphone. However, the monaural SE lags performance behind multi-channel SE as the monaural SE methods are unable to extract spatial information from one-channel recordings, which greatly limits their application scenarios. To address this issue, we inject spatial information into the monaural SE model and propose a knowledge distillation strategy to enable the monaural SE model to learn binaural speech features from the binaural SE model, which makes monaural S…
A conventional approach to improving the performance of end-to-end speech translation (E2E-ST) models is to leverage the source transcription via pre-training and joint training with automatic speech recognition (ASR) and neural machine translation (NMT) tasks. However, since the input modalities are different, it is difficult to leverage source language text successfully. In this work, we focus on sequence-level knowledge distillation (SeqKD) from external text-based NMT models. To leverage the full potential of the source language information, we propose backward SeqKD, SeqKD from a target-t…
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）
This paper describes FBK's participation in the IWSLT 2020 offline speech translation (ST) task. The task evaluates systems' ability to translate English TED talks audio into German texts. The test talks are provided in two versions: one contains the data already segmented with automatic tools and the other is the raw data without any segmentation. Participants can decide whether to work on custom segmentation or not. We used the provided segmentation. Our system is an end-to-end model based on an adaptation of the Transformer for speech data. Its training process is the main focus of this pap…
While deep learning systems have gained significant ground in speech enhancement research, these systems have yet to make use of the full potential of deep learning systems to provide high-level feedback. In particular, phonetic feedback is rare in speech enhancement research even though it includes valuable top-down information. We use the technique of mimic loss to provide phonetic feedback to an off-the-shelf enhancement system, and find gains in objective intelligibility scores on CHiME-4 data. This technique takes a frozen acoustic model trained on clean speech to provide valuable feedbac…
Personalized speech enhancement (PSE) models achieve promising results compared with unconditional speech enhancement models due to their ability to remove interfering speech in addition to background noise. Unlike unconditional speech enhancement, causal PSE models may occasionally remove the target speech by mistake. The PSE models also tend to leak interfering speech when the target speaker is silent for an extended period. We show that existing PSE methods suffer from a trade-off between speech over-suppression and interference leakage by addressing one problem at the expense of the other.…
Monaural speech enhancement has made dramatic advances since the introduction of deep learning a few years ago. Although enhanced speech has been demonstrated to have better intelligibility and quality for human listeners, feeding it directly to automatic speech recognition (ASR) systems trained with noisy speech has not produced expected improvements in ASR performance. The lack of an enhancement benefit on recognition, or the gap between monaural speech enhancement and recognition, is often attributed to speech distortions introduced in the enhancement process. In this study, we analyze the …
Large-scale speech self-supervised learning (SSL) has emerged to the main field of speech processing, however, the problem of computational cost arising from its vast size makes a high entry barrier to academia. In addition, existing distillation techniques of speech SSL models compress the model by reducing layers, which induces performance degradation in linguistic pattern recognition tasks such as phoneme recognition (PR). In this paper, we propose FitHuBERT, which makes thinner in dimension throughout almost all model components and deeper in layer compared to prior speech SSL distillation…
Incorporating Ultrasound Tongue Images for Audio-Visual Speech Enhancement through Knowledge Distillation
National Engineering Research Center of Speech and Language Information Processing, University of Science and Technology of China（中国科学技术大学国家语言语音信息处理工程研究中心）
Self-supervised learning (SSL) is seen as a very promising approach with high performance for several speech downstream tasks. Since the parameters of SSL models are generally so large that training and inference require a lot of memory and computational cost, it is desirable to produce compact SSL models without a significant performance degradation by applying compression methods such as knowledge distillation (KD). Although the KD approach is able to shrink the depth and/or width of SSL model structures, there has been little research on how varying the depth and width impacts the internal …
While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. Here speech enhancement methods have traditionally allowed improved performance. The recent works have shown that adapting speech enhancement can lead to further gains. This paper introduces a novel approach that cascades speech enhancement and speaker recognition. In the first step, a speaker embedding vector is generated , which is used in the second step to enhance the speech quality and re-identify the speakers. Models …
Fondazione Bruno Kessler（布鲁诺·凯斯勒基金会）；University of Trento（特伦托大学）；AppTek
Direct speech translation (ST) has shown to be a complex task requiring knowledge transfer from its sub-tasks: automatic speech recognition (ASR) and machine translation (MT). For MT, one of the most promising techniques to transfer knowledge is knowledge distillation. In this paper, we compare the different solutions to distill knowledge in a sequence-to-sequence task like ST. Moreover, we analyze eventual drawbacks of this approach and how to alleviate them maintaining the benefits in terms of translation quality.
Supervised speech enhancement relies on parallel databases of degraded speech signals and their clean reference signals during training. This setting prohibits the use of real-world degraded speech data that may better represent the scenarios where such systems are used. In this paper, we explore methods that enable supervised speech enhancement systems to train on real-world degraded speech data. Specifically, we propose a semi-supervised approach for speech enhancement in which we first train a modified vector-quantized variational autoencoder that solves a source separation task. We then us…
The remarkable performance of the pre-trained language model (LM) using self-supervised learning has led to a major paradigm shift in the study of natural language processing. In line with these changes, leveraging the performance of speech recognition systems with massive deep learning-based LMs is a major topic of speech recognition research. Among the various methods of applying LMs to speech recognition systems, in this paper, we focus on a cross-modal knowledge distillation method that transfers knowledge between two types of deep neural networks with different modalities. We propose an a…
This paper investigates how to improve the runtime speed of personalized speech enhancement (PSE) networks while maintaining the model quality. Our approach includes two aspects: architecture and knowledge distillation (KD). We propose an end-to-end enhancement (E3Net) model architecture, which is $3\times$ faster than a baseline STFT-based model. Besides, we use KD techniques to develop compressed student models without significantly degrading quality. In addition, we investigate using noisy data without reference clean signals for training the student models, where we combine KD with multi-t…
Leveraging Local and Global Knowledge Integration with Time-Frequency Calibrated Distillation for Speech Enhancement
School of Computer Science, Nanjing Audit University（南京审计大学计算机科学学院）；School of Communication Engineering, Nanjing Institute of Technology（南京工程技术学院通信工程学院）；School of Information Science and Engineering, Southeast University（东南大学信息科学与工程学院）；Cardiff University（卡迪夫大学）；Inner Mongolia University（内蒙古大学）；CHI – the Chair of Health Informatics, TUM University Hospital（健康信息学系，技术大学医院）；GLAM – the Group on Language, Audio, & Music, Imperial College London（语言、音频与音乐组，伦敦帝国理工学院）；Xiaomi EV（小米电动车）
Speech enhancement methods based on deep learning have surpassed traditional methods. While many of these new approaches are operating on the wideband (16kHz) sample rate, a new fullband (48kHz) speech enhancement system is proposed in this paper. Compared to the existing fullband systems that utilizes perceptually motivated features to train the fullband speech enhancement using a single network structure, the proposed system is a two-step system ensuring good fullband speech enhancement quality while backward compatible to the existing wideband systems.
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）
Existing speech enhancement methods mainly separate speech from noises at the signal level or in the time-frequency domain. They seldom pay attention to the semantic information of a corrupted signal. In this paper, we aim to bridge this gap by extracting phoneme identities to help speech enhancement. Specifically, we propose a phoneme-based distribution regularization (PbDr) for speech enhancement, which incorporates frame-wise phoneme information into speech enhancement network in a conditional manner. As different phonemes always lead to different feature distributions in frequency, we prop…
In this work, we propose a technique to transfer speech recognition capabilities from audio speech recognition systems to visual speech recognizers, where our goal is to utilize audio data during lipreading model training. Impressive progress in the domain of speech recognition has been exhibited by audio and audio-visual systems. Nevertheless, there is still much to be explored with regards to visual speech recognition systems due to the visual ambiguity of some phonemes. To this end, the development of visual speech recognition models is crucial given the instability of audio models. The mai…
This report focuses on algorithms that perform single-channel speech enhancement. The author of this report uses modulation-domain Kalman filtering algorithms for speech enhancement, i.e. noise suppression and dereverberation, in [1], [2], [3], [4] and [5]. Modulation-domain Kalman filtering can be applied for both noise and late reverberation suppression and in [2], [1], [3] and [4], various model-based speech enhancement algorithms that perform modulation-domain Kalman filtering are designed, implemented and tested. The model-based enhancement algorithm in [2] estimates and tracks the speech…
Objective and Subjective Evaluation of Diffusion-Based Speech Enhancement for Dysarthric Speech
Delft University of Technology（代尔夫特理工大学）；Erasmus Medical Centre (EMC)（埃因霍温医学院）；Indian Inst. of Information Technology Allahabad（阿利哈巴德信息科技学院）；Dept. of Plastic and Reconstructive Surgery（整形外科与重建外科系）；Dept. of Electronics and Communication（电子与通信系）
Single-channel speech enhancement with deep neural networks (DNNs) has shown promising performance and is thus intensively being studied. In this paper, instead of applying the mean squared error (MSE) as the loss function during DNN training for speech enhancement, we design a perceptual weighting filter loss motivated by the weighting filter as it is employed in analysis-by-synthesis speech coding, e.g., in code-excited linear prediction (CELP). The experimental results show that the proposed simple loss function improves the speech enhancement performance compared to a reference DNN with MS…
National Institute of Informatics（国立情报学研究所）；The Graduate University for Advanced Studies (SOKENDAI)（综合研究大学院大学（SOKENDAI））
Speech enhancement (SE) methods mainly focus on recovering clean speech from noisy input. In real-world speech communication, however, noises often exist in not only speaker but also listener environments. Although SE methods can suppress the noise contained in the speaker's voice, they cannot deal with the noise that is physically present in the listener side. To address such a complicated but common scenario, we investigate a deep learning-based joint framework integrating noise reduction (NR) with listening enhancement (LE), in which the NR module first suppresses noise and the LE module th…
Acoustic echo cancellation (AEC) plays an important role in the full-duplex speech communication as well as the front-end speech enhancement for recognition in the conditions when the loudspeaker plays back. In this paper, we present an all-deep-learning framework that implicitly estimates the second order statistics of echo/noise and target speech, and jointly solves echo and noise suppression through an attention based recurrent neural network. The proposed model outperforms the state-of-the-art joint echo cancellation and speech enhancement method F-T-LSTM in terms of objective speech quali…
Several solutions for lightweight TTS have shown promising results. Still, they either rely on a hand-crafted design that reaches non-optimum size or use a neural architecture search but often suffer training costs. We present Nix-TTS, a lightweight TTS achieved via knowledge distillation to a high-quality yet large-sized, non-autoregressive, and end-to-end (vocoder-free) TTS teacher model. Specifically, we offer module-wise distillation, enabling flexible and independent distillation to the encoder and decoder module. The resulting Nix-TTS inherited the advantageous properties of being non-au…
Estimating dimensional emotions, such as activation, valence and dominance, from acoustic speech signals has been widely explored over the past few years. While accurate estimation of activation and dominance from speech seem to be possible, the same for valence remains challenging. Previous research has shown that the use of lexical information can improve valence estimation performance. Lexical information can be obtained from pre-trained acoustic models, where the learned representations can improve valence estimation from speech. We investigate the use of pre-trained model representations …
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 s…
This letter introduces a novel speech enhancement method in the Hilbert-Huang Transform domain to mitigate the effects of acoustic impulsive noises. The estimation and selection of noise components is based on the impulsiveness index of decomposition modes. Speech enhancement experiments are conducted considering five acoustic noises with different impulsiveness index and non-stationarity degrees under various signal-to-noise ratios. Three speech enhancement algorithms are adopted as baseline in the evaluation analysis considering spectral and time domains. The proposed solution achieves the b…
In realistic speech enhancement settings for end-user devices, we often encounter only a few speakers and noise types that tend to reoccur in the specific acoustic environment. We propose a novel personalized speech enhancement method to adapt a compact denoising model to the test-time specificity. Our goal in this test-time adaptation is to utilize no clean speech target of the test speaker, thus fulfilling the requirement for zero-shot learning. To complement the lack of clean utterance, we employ the knowledge distillation framework. Instead of the missing clean utterance target, we distill…
Spectral mask estimation using bidirectional long short-term memory (BLSTM) neural networks has been widely used in various speech enhancement applications, and it has achieved great success when it is applied to multichannel enhancement techniques with a mask-based beamformer. However, when these masks are used for single channel speech enhancement they severely distort the speech signal and make them unsuitable for speech recognition. This paper proposes a student-teacher learning paradigm for single channel speech enhancement. The beamformed signal from multichannel enhancement is given as …
Institute for Information & communications Technology Promotion（信息与通信技术振兴院）；Microsoft Research Asia（微软亚洲研究院）
There is a surge in interest in self-supervised learning approaches for end-to-end speech encoding in recent years as they have achieved great success. Especially, WavLM showed state-of-the-art performance on various speech processing tasks. To better understand the efficacy of self-supervised learning models for speech enhancement, in this work, we design and conduct a series of experiments with three resource conditions by combining WavLM and two high-quality speech enhancement systems. Also, we propose a regression-based WavLM training objective and a noise-mixing data configuration to furt…
We present an introspection of an audiovisual speech enhancement model. In particular, we focus on interpreting how a neural audiovisual speech enhancement model uses visual cues to improve the quality of the target speech signal. We show that visual cues provide not only high-level information about speech activity, i.e., speech/silence, but also fine-grained visual information about the place of articulation. One byproduct of this finding is that the learned visual embeddings can be used as features for other visual speech applications. We demonstrate the effectiveness of the learned visual …
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）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）；Baidu Inc.（百度公司）
End-to-end speech translation (ST), which directly translates from source language speech into target language text, has attracted intensive attentions in recent years. Compared to conventional pipeline systems, end-to-end ST models have advantages of lower latency, smaller model size and less error propagation. However, the combination of speech recognition and text translation in one model is more difficult than each of these two tasks. In this paper, we propose a knowledge distillation approach to improve ST model by transferring the knowledge from text translation model. Specifically, we f…
Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education, Anhui University（安徽大学智能计算与信号处理教育部重点实验室）
Compared with air-conducted speech, bone-conducted speech has the unique advantage of shielding background noise. Enhancement of bone-conducted speech helps to improve its quality and intelligibility. In this paper, a novel CycleGAN with dual adversarial loss (CycleGAN-DAL) is proposed for bone-conducted speech enhancement. The proposed method uses an adversarial loss and a cycle-consistent loss simultaneously to learn forward and cyclic mapping, in which the adversarial loss is replaced with the classification adversarial loss and the defect adversarial loss to consolidate the forward mapping…
This paper proposes a dual-stage, low complexity, and reconfigurable technique to enhance the speech contaminated by various types of noise sources. Driven by input data and audio contents, the proposed dual-stage speech enhancement approach performs a coarse and fine processing in the first-stage and second-stage, respectively. In this paper, we demonstrate that the proposed speech enhancement solution significantly enhances the metrics of 3-fold QUality Evaluation of Speech in Telecommunication (3QUEST) consisting of speech mean-opinion-score (SMOS) and noise MOS (NMOS) for near-field and fa…
Deep neural network (DNN)-based speech enhancement usually uses a clean speech as a training target. However, it is hard to collect large amounts of clean speech because the recording is very costly. In other words, the performance of current speech enhancement has been limited by the amount of training data. To relax this limitation, Noisy-target Training (NyTT) that utilizes noisy speech as a training target has been proposed. Although it has been experimentally shown that NyTT can train a DNN without clean speech, a detailed analysis has not been conducted and its behavior has not been unde…
