Get our free extension to see links to code for papers anywhere online!

Chrome logo  Add to Chrome

Firefox logo Add to Firefox

"speech recognition": models, code, and papers

Introduction to Arabic Speech Recognition Using CMUSphinx System

Apr 17, 2007
H. Satori, M. Harti, N. Chenfour

In this paper Arabic was investigated from the speech recognition problem point of view. We propose a novel approach to build an Arabic Automated Speech Recognition System (ASR). This system is based on the open source CMU Sphinx-4, from the Carnegie Mellon University. CMU Sphinx is a large-vocabulary; speaker-independent, continuous speech recognition system based on discrete Hidden Markov Models (HMMs). We build a model using utilities from the OpenSource CMU Sphinx. We will demonstrate the possible adaptability of this system to Arabic voice recognition.

* 4 pages, 3 figures and 2 tables, was in Information and Communication Technologies International Symposium proceeding ICTIS07 Fes (2007) 
Access Paper or Ask Questions

Cross-lingual Self-Supervised Speech Representations for Improved Dysarthric Speech Recognition

Apr 04, 2022
Abner Hernandez, Paula Andrea Pérez-Toro, Elmar Nöth, Juan Rafael Orozco-Arroyave, Andreas Maier, Seung Hee Yang

State-of-the-art automatic speech recognition (ASR) systems perform well on healthy speech. However, the performance on impaired speech still remains an issue. The current study explores the usefulness of using Wav2Vec self-supervised speech representations as features for training an ASR system for dysarthric speech. Dysarthric speech recognition is particularly difficult as several aspects of speech such as articulation, prosody and phonation can be impaired. Specifically, we train an acoustic model with features extracted from Wav2Vec, Hubert, and the cross-lingual XLSR model. Results suggest that speech representations pretrained on large unlabelled data can improve word error rate (WER) performance. In particular, features from the multilingual model led to lower WERs than filterbanks (Fbank) or models trained on a single language. Improvements were observed in English speakers with cerebral palsy caused dysarthria (UASpeech corpus), Spanish speakers with Parkinsonian dysarthria (PC-GITA corpus) and Italian speakers with paralysis-based dysarthria (EasyCall corpus). Compared to using Fbank features, XLSR-based features reduced WERs by 6.8%, 22.0%, and 7.0% for the UASpeech, PC-GITA, and EasyCall corpus, respectively.

* Submitted for review at Interspeech 2022 
Access Paper or Ask Questions

Streaming end-to-end speech recognition with jointly trained neural feature enhancement

May 04, 2021
Chanwoo Kim, Abhinav Garg, Dhananjaya Gowda, Seongkyu Mun, Changwoo Han

In this paper, we present a streaming end-to-end speech recognition model based on Monotonic Chunkwise Attention (MoCha) jointly trained with enhancement layers. Even though the MoCha attention enables streaming speech recognition with recognition accuracy comparable to a full attention-based approach, training this model is sensitive to various factors such as the difficulty of training examples, hyper-parameters, and so on. Because of these issues, speech recognition accuracy of a MoCha-based model for clean speech drops significantly when a multi-style training approach is applied. Inspired by Curriculum Learning [1], we introduce two training strategies: Gradual Application of Enhanced Features (GAEF) and Gradual Reduction of Enhanced Loss (GREL). With GAEF, the model is initially trained using clean features. Subsequently, the portion of outputs from the enhancement layers gradually increases. With GREL, the portion of the Mean Squared Error (MSE) loss for the enhanced output gradually reduces as training proceeds. In experimental results on the LibriSpeech corpus and noisy far-field test sets, the proposed model with GAEF-GREL training strategies shows significantly better results than the conventional multi-style training approach.

* Accepted to ICASSP 2021 
Access Paper or Ask Questions

ESE: Efficient Speech Recognition Engine with Sparse LSTM on FPGA

Feb 20, 2017
Song Han, Junlong Kang, Huizi Mao, Yiming Hu, Xin Li, Yubin Li, Dongliang Xie, Hong Luo, Song Yao, Yu Wang, Huazhong Yang, William J. Dally

Long Short-Term Memory (LSTM) is widely used in speech recognition. In order to achieve higher prediction accuracy, machine learning scientists have built larger and larger models. Such large model is both computation intensive and memory intensive. Deploying such bulky model results in high power consumption and leads to high total cost of ownership (TCO) of a data center. In order to speedup the prediction and make it energy efficient, we first propose a load-balance-aware pruning method that can compress the LSTM model size by 20x (10x from pruning and 2x from quantization) with negligible loss of the prediction accuracy. The pruned model is friendly for parallel processing. Next, we propose scheduler that encodes and partitions the compressed model to each PE for parallelism, and schedule the complicated LSTM data flow. Finally, we design the hardware architecture, named Efficient Speech Recognition Engine (ESE) that works directly on the compressed model. Implemented on Xilinx XCKU060 FPGA running at 200MHz, ESE has a performance of 282 GOPS working directly on the compressed LSTM network, corresponding to 2.52 TOPS on the uncompressed one, and processes a full LSTM for speech recognition with a power dissipation of 41 Watts. Evaluated on the LSTM for speech recognition benchmark, ESE is 43x and 3x faster than Core i7 5930k CPU and Pascal Titan X GPU implementations. It achieves 40x and 11.5x higher energy efficiency compared with the CPU and GPU respectively.

* Accepted as full paper in FPGA'17, Monterey, CA; Also appeared at 1st International Workshop on Efficient Methods for Deep Neural Networks at NIPS 2016, Barcelona, Spain 
Access Paper or Ask Questions

Towards End-to-end Unsupervised Speech Recognition

Apr 05, 2022
Alexander H. Liu, Wei-Ning Hsu, Michael Auli, Alexei Baevski

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of making supervised speech recognition end-to-end, we introduce \wvu~which does away with all audio-side pre-processing and improves accuracy through better architecture. In addition, we introduce an auxiliary self-supervised objective that ties model predictions back to the input. Experiments show that \wvu~improves unsupervised recognition results across different languages while being conceptually simpler.

* Preprint 
Access Paper or Ask Questions

Noise-robust Speech Recognition with 10 Minutes Unparalleled In-domain Data

Mar 29, 2022
Chen Chen, Nana Hou, Yuchen Hu, Shashank Shirol, Eng Siong Chng

Noise-robust speech recognition systems require large amounts of training data including noisy speech data and corresponding transcripts to achieve state-of-the-art performances in face of various practical environments. However, such plenty of in-domain data is not always available in the real-life world. In this paper, we propose a generative adversarial network to simulate noisy spectrum from the clean spectrum (Simu-GAN), where only 10 minutes of unparalleled in-domain noisy speech data is required as labels. Furthermore, we also propose a dual-path speech recognition system to improve the robustness of the system under noisy conditions. Experimental results show that the proposed speech recognition system achieves 7.3% absolute improvement with simulated noisy data by Simu-GAN over the best baseline in terms of word error rate (WER).

* Accepted by ICASSP2022 
Access Paper or Ask Questions

Transfer Learning from Adult to Children for Speech Recognition: Evaluation, Analysis and Recommendations

May 08, 2018
Prashanth Gurunath Shivakumar, Panayiotis Georgiou

Children speech recognition is challenging mainly due to the inherent high variability in children's physical and articulatory characteristics and expressions. This variability manifests in both acoustic constructs and linguistic usage due to the rapidly changing developmental stage in children's life. Part of the challenge is due to the lack of large amounts of available children speech data for efficient modeling. This work attempts to address the key challenges using transfer learning from adult's models to children's models in a Deep Neural Network (DNN) framework for children's Automatic Speech Recognition (ASR) task evaluating on multiple children's speech corpora with a large vocabulary. The paper presents a systematic and an extensive analysis of the proposed transfer learning technique considering the key factors affecting children's speech recognition from prior literature. Evaluations are presented on (i) comparisons of earlier GMM-HMM and the newer DNN Models, (ii) effectiveness of standard adaptation techniques versus transfer learning, (iii) various adaptation configurations in tackling the variabilities present in children speech, in terms of (a) acoustic spectral variability, and (b) pronunciation variability and linguistic constraints. Our Analysis spans over (i) number of DNN model parameters (for adaptation), (ii) amount of adaptation data, (iii) ages of children, (iv) age dependent-independent adaptation. Finally, we provide Recommendations on (i) the favorable strategies over various aforementioned - analyzed parameters, and (ii) potential future research directions and relevant challenges/problems persisting in DNN based ASR for children's speech.

Access Paper or Ask Questions

Integrated speech and morphological processing in a connectionist continuous speech understanding for Korean

Mar 18, 1996
Geunbae Lee, Jong-Hyeok Lee

A new tightly coupled speech and natural language integration model is presented for a TDNN-based continuous possibly large vocabulary speech recognition system for Korean. Unlike popular n-best techniques developed for integrating mainly HMM-based speech recognition and natural language processing in a {\em word level}, which is obviously inadequate for morphologically complex agglutinative languages, our model constructs a spoken language system based on a {\em morpheme-level} speech and language integration. With this integration scheme, the spoken Korean processing engine (SKOPE) is designed and implemented using a TDNN-based diphone recognition module integrated with a Viterbi-based lexical decoding and symbolic phonological/morphological co-analysis. Our experiment results show that the speaker-dependent continuous {\em eojeol} (Korean word) recognition and integrated morphological analysis can be achieved with over 80.6% success rate directly from speech inputs for the middle-level vocabularies.

* latex source with a4 style, 15 pages, to be published in computer processing of oriental language journal 
Access Paper or Ask Questions

Self-supervised Learning with Random-projection Quantizer for Speech Recognition

Feb 03, 2022
Chung-Cheng Chiu, James Qin, Yu Zhang, Jiahui Yu, Yonghui Wu

We present a simple and effective self-supervised learning approach for speech recognition. The approach learns a model to predict the masked speech signals, in the form of discrete labels generated with a random-projection quantizer. In particular the quantizer projects speech inputs with a randomly initialized matrix, and does a nearest-neighbor lookup in a randomly-initialized codebook. Neither the matrix nor the codebook is updated during self-supervised learning. Since the random-projection quantizer is not trained and is separated from the speech recognition model, the design makes the approach flexible and is compatible with universal speech recognition architecture. On LibriSpeech our approach achieves similar word-error-rates as previous work using self-supervised learning with non-streaming models, and provides lower word-error-rates and latency than wav2vec 2.0 and w2v-BERT with streaming models. On multilingual tasks the approach also provides significant improvement over wav2vec 2.0 and w2v-BERT.

Access Paper or Ask Questions

Progressive Joint Modeling in Unsupervised Single-channel Overlapped Speech Recognition

Oct 20, 2017
Zhehuai Chen, Jasha Droppo, Jinyu Li, Wayne Xiong

Unsupervised single-channel overlapped speech recognition is one of the hardest problems in automatic speech recognition (ASR). Permutation invariant training (PIT) is a state of the art model-based approach, which applies a single neural network to solve this single-input, multiple-output modeling problem. We propose to advance the current state of the art by imposing a modular structure on the neural network, applying a progressive pretraining regimen, and improving the objective function with transfer learning and a discriminative training criterion. The modular structure splits the problem into three sub-tasks: frame-wise interpreting, utterance-level speaker tracing, and speech recognition. The pretraining regimen uses these modules to solve progressively harder tasks. Transfer learning leverages parallel clean speech to improve the training targets for the network. Our discriminative training formulation is a modification of standard formulations, that also penalizes competing outputs of the system. Experiments are conducted on the artificial overlapped Switchboard and hub5e-swb dataset. The proposed framework achieves over 30% relative improvement of WER over both a strong jointly trained system, PIT for ASR, and a separately optimized system, PIT for speech separation with clean speech ASR model. The improvement comes from better model generalization, training efficiency and the sequence level linguistic knowledge integration.

* IEEE/ACM Transactions on Audio, Speech, and Language Processing, 26 (2018) 184-196 
* submitted to TASLP, 07/20/2017; accepted by TASLP, 10/13/2017 
Access Paper or Ask Questions