In this work, we propose lattice-free MMI (LFMMI) for supervised adaptation of self-supervised pretrained acoustic model. We pretrain a Transformer model on thousand hours of untranscribed Librispeech data followed by supervised adaptation with LFMMI on three different datasets. Our results show that fine-tuning with LFMMI, we consistently obtain relative WER improvements of 10% and 35.3% on the clean and other test sets of Librispeech (100h), 10.8% on Switchboard (300h), and 4.3% on Swahili (38h) and 4.4% on Tagalog (84h) compared to the baseline trained only with supervised data.
We present a simple wrapper that is useful to train acoustic models in PyTorch using Kaldi's LF-MMI training framework. The wrapper, called pkwrap (short form of PyTorch kaldi wrapper), enables the user to utilize the flexibility provided by PyTorch in designing model architectures. It exposes the LF-MMI cost function as an autograd function. Other capabilities of Kaldi have also been ported to PyTorch. This includes the parallel training ability when multi-GPU environments are unavailable and decode with graphs created in Kaldi. The package is available on Github at https://github.com/idiap/p…
In the broadcast domain there is an abundance of related text data and partial transcriptions, such as closed captions and subtitles. This text data can be used for lightly supervised training, in which text matching the audio is selected using an existing speech recognition model. Current approaches to light supervision typically filter the data based on matching error rates between the transcriptions and biased decoding hypotheses. In contrast, semi-supervised training does not require matching text data, instead generating a hypothesis using a background language model. State-of-the-art sem…
In this work, we investigate the effectiveness of pretrained Self-Supervised Learning (SSL) features for learning the mapping for acoustic to articulatory inversion (AAI). Signal processing-based acoustic features such as MFCCs have been predominantly used for the AAI task with deep neural networks. With SSL features working well for various other speech tasks such as speech recognition, emotion classification, etc., we experiment with its efficacy for AAI. We train on SSL features with transformer neural networks-based AAI models of 3 different model complexities and compare its performance w…
Tencent Cloud Xiaowei（腾讯云小微）；Institute of Acoustics, Chinese Academy of Sciences（中国科学院声学研究所）；University of Chinese Academy of Sciences（中国科学院大学）
Recently, self-supervised pretraining has achieved impressive results in end-to-end (E2E) automatic speech recognition (ASR). However, the dominant sequence-to-sequence (S2S) E2E model is still hard to fully utilize the self-supervised pre-training methods because its decoder is conditioned on acoustic representation thus cannot be pretrained separately. In this paper, we propose a pretrained Transformer (Preformer) S2S ASR architecture based on hybrid CTC/attention E2E models to fully utilize the pretrained acoustic models (AMs) and language models (LMs). In our framework, the encoder is init…
State-of-the-art hybrid automatic speech recognition (ASR) system exploits deep neural network (DNN) based acoustic models (AM) trained with Lattice Free-Maximum Mutual Information (LF-MMI) criterion and n-gram language models. The AMs typically have millions of parameters and require significant parameter reduction to operate on embedded devices. The impact of parameter quantization on the overall word recognition performance is studied in this paper. Following approaches are presented: (i) AM trained in Kaldi framework with conventional factorized TDNN (TDNN-F) architecture, (ii) the TDNN AM…
In this work, we investigate if the wav2vec 2.0 self-supervised pretraining helps mitigate the overfitting issues with connectionist temporal classification (CTC) training to reduce its performance gap with flat-start lattice-free MMI (E2E-LFMMI) for automatic speech recognition with limited training data. Towards that objective, we use the pretrained wav2vec 2.0 BASE model and fine-tune it on three different datasets including out-of-domain (Switchboard) and cross-lingual (Babel) scenarios. Our results show that for supervised adaptation of the wav2vec 2.0 model, both E2E-LFMMI and CTC achiev…
Spoken language understanding is typically based on pipeline architectures including speech recognition and natural language understanding steps. These components are optimized independently to allow usage of available data, but the overall system suffers from error propagation. In this paper, we propose a novel training method that enables pretrained contextual embeddings to process acoustic features. In particular, we extend it with an encoder of pretrained speech recognition systems in order to construct end-to-end spoken language understanding systems. Our proposed method is based on the t…
Acoustic model adaptation to unseen test recordings aims to reduce the mismatch between training and testing conditions. Most adaptation schemes for neural network models require the use of an initial one-best transcription for the test data, generated by an unadapted model, in order to estimate the adaptation transform. It has been found that adaptation methods using discriminative objective functions - such as cross-entropy loss - often require careful regularisation to avoid over-fitting to errors in the one-best transcriptions. In this paper we solve this problem by performing discriminati…
In this work, three lattice-free (LF) discriminative training criteria for purely sequence-trained neural network acoustic models are compared on LVCSR tasks, namely maximum mutual information (MMI), boosted maximum mutual information (bMMI) and state-level minimum Bayes risk (sMBR). We demonstrate that, analogous to LF-MMI, a neural network acoustic model can also be trained from scratch using LF-bMMI or LF-sMBR criteria respectively without the need of cross-entropy pre-training. Furthermore, experimental results on Switchboard-300hrs and Switchboard+Fisher-2100hrs datasets show that models …
Sequence discriminative training criteria have long been a standard tool in automatic speech recognition for improving the performance of acoustic models over their maximum likelihood / cross entropy trained counterparts. While previously a lattice approximation of the search space has been necessary to reduce computational complexity, recently proposed methods use other approximations to dispense of the need for the computationally expensive step of separate lattice creation. In this work we present a memory efficient implementation of the forward-backward computation that allows us to use un…
Towards developing high-performing ASR for low-resource languages, approaches to address the lack of resources are to make use of data from multiple languages, and to augment the training data by creating acoustic variations. In this work we present a single grapheme-based ASR model learned on 7 geographically proximal languages, using standard hybrid BLSTM-HMM acoustic models with lattice-free MMI objective. We build the single ASR grapheme set via taking the union over each language-specific grapheme set, and we find such multilingual graphemic hybrid ASR model can perform language-independe…
State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as the mapping from the written form to the spoken form is complicated. However, in recent years the representational power of deep-learning based acoustic models has improved, raising interest in graphemic acoustic models for English, due to the simplicity of generating the lexicon. In this paper, phonetic and graphemic models are compared for an English Multi-Genre Broadcast transcription task. A range of acoustic mo…
Unsupervised and self-supervised learning methods have leveraged unlabelled data to improve the pretrained models. However, these methods need significantly large amount of unlabelled data and the computational cost of training models with such large amount of data can be prohibitively high. We address this issue by using unlabelled data during finetuning, instead of pretraining. We propose acoustic model finetuning (FT) using labelled and unlabelled data. The model is jointly trained to learn representations to classify senones, as well as learn contextual acoustic representations. Our traini…
University of Illinois（伊利诺伊大学）；Beckman Institute（贝克曼研究所）；Novumind Inc（诺维明德公司）；Amazon Alexa Speech（亚马逊Alexa语音部门）
Connectionist temporal classification (CTC) provides an end-to-end acoustic model (AM) training strategy. CTC learns accurate AMs without time-aligned phonetic transcription, but sometimes fails to converge, especially in resource-constrained scenarios. In this paper, the convergence properties of CTC are improved by incorporating acoustic landmarks. We tailored a new set of acoustic landmarks to help CTC training converge more rapidly and smoothly while also reducing recognition error rates. We leveraged new target label sequences mixed with both phone and manner changes to guide CTC training…
In this paper, we investigate representation learning for low-resource keyword spotting (KWS). The main challenges of KWS are limited labeled data and limited available device resources. To address those challenges, we explore representation learning for KWS by self-supervised contrastive learning and self-training with pretrained model. First, local-global contrastive siamese networks (LGCSiam) are designed to learn similar utterance-level representations for similar audio samplers by proposed local-global contrastive loss without requiring ground-truth. Second, a self-supervised pretrained W…
Read What You Hear: Reference-Free Hypotheses Evaluation with Acoustic Discrepancy
X-LANCE Lab, School of Computer Science, Shanghai Jiao Tong University, China（X-LANCE实验室、计算机科学学院、上海交通大学、中国）；MoE Key Lab of Artificial Intelligence, Jiangsu Key Lab of Language Computing, China（人工智能MOE重点实验室、江苏省语言计算重点实验室、中国）
Temporal Order Preserved Optimal Transport-based Cross-modal Knowledge Transfer Learning for ASR
National Institute of Information and Communications Technology（信息通信研究机构）；Research Center for Information Technology Innovation（资讯科技创新研究中心）；Academia Sinica（中央研究院）
Brouhaha: multi-task training for voice activity detection, speech-to-noise ratio, and C50 room acoustics estimation
PSL University（巴黎文理研究大学）；CNRS（法国国家科学研究中心）；EHESS（法国高等社会科学研究院）；ENS（巴黎高等师范学院）；Meta AI Research（Meta人工智能研究院）；Duke University（杜克大学）；Université de Toulouse（图卢兹大学）
End-to-end speech recognition is a promising technology for enabling compact automatic speech recognition (ASR) systems since it can unify the acoustic and language model into a single neural network. However, as a drawback, training of end-to-end speech recognizers always requires transcribed utterances. Since end-to-end models are also known to be severely data hungry, this constraint is crucial especially because obtaining transcribed utterances is costly and can possibly be impractical or impossible. This paper proposes a method for alleviating this issue by transferring knowledge from a l…
Hybrid automatic speech recognition (ASR) models are typically sequentially trained with CTC or LF-MMI criteria. However, they have vastly different legacies and are usually implemented in different frameworks. In this paper, by decoupling the concepts of modeling units and label topologies and building proper numerator/denominator graphs accordingly, we establish a generalized framework for hybrid acoustic modeling (AM). In this framework, we show that LF-MMI is a powerful training criterion applicable to both limited-context and full-context models, for wordpiece/mono-char/bi-char/chenone un…
Cross-modal Alignment with Optimal Transport for CTC-based ASR
National Institute of Information and Communications Technology（国立信息与通信技术研究所）；Research Center for Information Technology Innovation, Academic Sinica（中央研究院资讯科技创新研究中心）
Laboratory of Algorithms and Technologies for Network Analysis（网络分析算法与技术实验室）；HSE University（高等经济大学）
This paper is focused on the finetuning of acoustic models for speaker adaptation goals on a given gender. We pretrained the Transformer baseline model on Librispeech-960 and conduct experiments with finetuning on the gender-specific test subsets and. In general, we do not obtain essential WER reduction by finetuning techniques by this approach. We achieved up to ~5% lower word error rate on the male subset and 3% on the female subset if the layers in the encoder and decoder are not frozen, but the tuning is started from the last checkpoints. Moreover, we adapted our base model on the full L2 …
Hierarchical Cross-Modality Knowledge Transfer with Sinkhorn Attention for CTC-based ASR
National Institute of Information and Communications Technology（日本国立信息与通信技术研究所）；Research Center for Information Technology Innovation, Academic Sinica（中央研究院资讯科技创新研究中心）
Maximum mutual information (MMI) has become one of the two de facto methods for sequence-level training of speech recognition acoustic models. This paper aims to isolate, identify and bring forward the implicit modelling decisions induced by the design implementation of standard finite state transducer (FST) lattice based MMI training framework. The paper particularly investigates the necessity to maintain a preselected numerator alignment and raises the importance of determinizing FST denominator lattices on the fly. The efficacy of employing on the fly FST lattice determinization is mathemat…
Recently, end-to-end (E2E) models, which allow to take spectral vector sequences of L2 (second-language) learners' utterances as input and produce the corresponding phone-level sequences as output, have attracted much research attention in developing mispronunciation detection (MD) systems. However, due to the lack of sufficient labeled speech data of L2 speakers for model estimation, E2E MD models are prone to overfitting in relation to conventional ones that are built on DNN-HMM acoustic models. To alleviate this critical issue, we in this paper propose two modeling strategies to enhance the…
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）
This paper proposes a novel approach to pre-train encoder-decoder sequence-to-sequence (seq2seq) model with unpaired speech and transcripts respectively. Our pre-training method is divided into two stages, named acoustic pre-trianing and linguistic pre-training. In the acoustic pre-training stage, we use a large amount of speech to pre-train the encoder by predicting masked speech feature chunks with its context. In the linguistic pre-training stage, we generate synthesized speech from a large number of transcripts using a single-speaker text to speech (TTS) system, and use the synthesized pai…
Air Traffic Management Research Institute, Nanyang Technological University, Singapore（新加坡南洋理工大学航空交通管理研究所）；Center of AI Research, VinUniversity, Vietnam（越南Vin大学人工智能研究中心）
Music Technology Group, Universitat Pompeu Fabra（庞培法布拉大学音乐技术组）
We propose a semi-supervised singing synthesizer, which is able to learn new voices from audio data only, without any annotations such as phonetic segmentation. Our system is an encoder-decoder model with two encoders, linguistic and acoustic, and one (acoustic) decoder. In a first step, the system is trained in a supervised manner, using a labelled multi-singer dataset. Here, we ensure that the embeddings produced by both encoders are similar, so that we can later use the model with either acoustic or linguistic input features. To learn a new voice in an unsupervised manner, the pretrained ac…
For self-supervised speech processing, it is crucial to use pretrained models as speech representation extractors. In recent works, increasing the size of the model has been utilized in acoustic model training in order to achieve better performance. In this paper, we propose Audio ALBERT, a lite version of the self-supervised speech representation model. We use the representations with two downstream tasks, speaker identification, and phoneme classification. We show that Audio ALBERT is capable of achieving competitive performance with those huge models in the downstream tasks while utilizing …
Linear probing enables Ship-Radiated Noise recognition with pretrained audio embeddings
Centre of Mathematics and Computer Science, Stochastics group（数学与计算机科学中心，随机组）；Vrije Universiteit, Department of Mathematics（自由大学，数学系）；Naturalis Biodiversity Center（自然多样性中心）
CommonAccent: Exploring Large Acoustic Pretrained Models for Accent Classification Based on Common Voice
Idiap Research Institute（Idiap研究所）；Ecole Polytechnique Federale de Lausanne（洛桑联邦理工学院）；Texas A&M University（得克萨斯农工大学）；Vilnius Gediminas Technical University（维尔纽斯盖迪米纳斯技术大学）；Université Laval（拉瓦尔大学）；Concordia University（康考迪亚大学）；Mila-Québec AI Institute（米拉-魁北克人工智能研究所）
Saw Swee Hock School of Public Health, National University of Singapore（新加坡国立大学苏瑞福公共卫生学院）；National University Health System, National University of Singapore（新加坡国立大学国立大学医疗系统）；National University Hospital, Singapore（新加坡国立大学医院）；Yong Loo Lin Medical School, National University of Singapore（新加坡国立大学杨潞龄医学院）；Institute of Data Science, National University of Singapore（新加坡国立大学数据科学研究所）
We suggested a unified system with core components of data augmentation, ImageNet-pretrained ResNet-50, cost-sensitive loss, deep ensemble learning, and uncertainty estimation to quickly and consistently detect COVID-19 using acoustic evidence. To increase the model's capacity to identify a minority class, data augmentation and cost-sensitive loss are incorporated (infected samples). In the COVID-19 detection challenge, ImageNet-pretrained ResNet-50 has been found to be effective. The unified framework also integrates deep ensemble learning and uncertainty estimation to integrate predictions f…
