An Investigation of End-to-End Models for Robust Speech Recognition

• URL: http://arxiv.org/abs/2102.06237v1
• Date: Thu, 11 Feb 2021 19:47:13 GMT
• Title: An Investigation of End-to-End Models for Robust Speech Recognition
• Authors: Archiki Prasad, Preethi Jyothi, Rajbabu Velmurugan
• Abstract summary: We present a comparison of speech enhancement-based techniques and three different model-based adaptation techniques for robust automatic speech recognition. While adversarial learning is the best-performing technique on certain noise types, it comes at the cost of degrading clean speech WER. On other relatively stationary noise types, a new speech enhancement technique outperformed all the model-based adaptation techniques.
• Score: 20.998349142078805
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: End-to-end models for robust automatic speech recognition (ASR) have not been sufficiently well-explored in prior work. With end-to-end models, one could choose to preprocess the input speech using speech enhancement techniques and train the model using enhanced speech. Another alternative is to pass the noisy speech as input and modify the model architecture to adapt to noisy speech. A systematic comparison of these two approaches for end-to-end robust ASR has not been attempted before. We address this gap and present a detailed comparison of speech enhancement-based techniques and three different model-based adaptation techniques covering data augmentation, multi-task learning, and adversarial learning for robust ASR. While adversarial learning is the best-performing technique on certain noise types, it comes at the cost of degrading clean speech WER. On other relatively stationary noise types, a new speech enhancement technique outperformed all the model-based adaptation techniques. This suggests that knowledge of the underlying noise type can meaningfully inform the choice of adaptation technique.

Related papers

• Multi-modal Adversarial Training for Zero-Shot Voice Cloning [9.823246184635103]
  We propose a Transformer encoder-decoder architecture to conditionally discriminate between real and generated speech features. We introduce our novel adversarial training technique by applying it to a FastSpeech2 acoustic model and training on Libriheavy, a large multi-speaker dataset. Our model achieves improvements over the baseline in terms of speech quality and speaker similarity.
  arXiv  Detail & Related papers  (2024-08-28T16:30:41Z)
• Contrastive and Consistency Learning for Neural Noisy-Channel Model in Spoken Language Understanding [1.07288078404291]
  We propose a natural language understanding approach based on Automatic Speech Recognition (ASR) We improve a noisy-channel model to handle transcription inconsistencies caused by ASR errors. Experiments on four benchmark datasets show that Contrastive and Consistency Learning (CCL) outperforms existing methods.
  arXiv  Detail & Related papers  (2024-05-23T23:10:23Z)
• Feature Normalization for Fine-tuning Self-Supervised Models in Speech Enhancement [19.632358491434697]
  Large, pre-trained representation models trained using self-supervised learning have gained popularity in various fields of machine learning. In this paper, we investigate the feasibility of using pre-trained speech representation models for a downstream speech enhancement task. Our proposed method enables significant improvements in speech quality compared to baselines when combined with various types of pre-trained speech models.
  arXiv  Detail & Related papers  (2023-06-14T10:03:33Z)
• Any-speaker Adaptive Text-To-Speech Synthesis with Diffusion Models [65.28001444321465]
  Grad-StyleSpeech is an any-speaker adaptive TTS framework based on a diffusion model. It can generate highly natural speech with extremely high similarity to target speakers' voice, given a few seconds of reference speech. It significantly outperforms speaker-adaptive TTS baselines on English benchmarks.
  arXiv  Detail & Related papers  (2022-11-17T07:17:24Z)
• Contextual-Utterance Training for Automatic Speech Recognition [65.4571135368178]
  We propose a contextual-utterance training technique which makes use of the previous and future contextual utterances. Also, we propose a dual-mode contextual-utterance training technique for streaming automatic speech recognition (ASR) systems. The proposed technique is able to reduce both the WER and the average last token emission latency by more than 6% and 40ms relative.
  arXiv  Detail & Related papers  (2022-10-27T08:10:44Z)
• A Systematic Comparison of Phonetic Aware Techniques for Speech Enhancement [20.329872147913584]
  We compare different methods of incorporating phonetic information in a speech enhancement model. We observe the influence of different phonetic content models as well as various feature-injection techniques on enhancement performance.
  arXiv  Detail & Related papers  (2022-06-22T12:00:50Z)
• An Exploration of Prompt Tuning on Generative Spoken Language Model for Speech Processing Tasks [112.1942546460814]
  We report the first exploration of the prompt tuning paradigm for speech processing tasks based on Generative Spoken Language Model (GSLM) Experiment results show that the prompt tuning technique achieves competitive performance in speech classification tasks with fewer trainable parameters than fine-tuning specialized downstream models.
  arXiv  Detail & Related papers  (2022-03-31T03:26:55Z)
• Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction [109.44933866397123]
  Noise robustness is essential for deploying automatic speech recognition systems in real-world environments. We employ a noise-robust representation learned by a refined self-supervised framework for noisy speech recognition. We achieve comparable performance to the best supervised approach reported with only 16% of labeled data.
  arXiv  Detail & Related papers  (2021-10-28T20:39:02Z)
• Knowledge Distillation from BERT Transformer to Speech Transformer for Intent Classification [66.62686601948455]
  We exploit the scope of the transformer distillation method that is specifically designed for knowledge distillation from a transformer based language model to a transformer based speech model. We achieve an intent classification accuracy of 99.10% and 88.79% for Fluent speech corpus and ATIS database, respectively.
  arXiv  Detail & Related papers  (2021-08-05T13:08:13Z)
• Pretraining Techniques for Sequence-to-Sequence Voice Conversion [57.65753150356411]
  Sequence-to-sequence (seq2seq) voice conversion (VC) models are attractive owing to their ability to convert prosody. We propose to transfer knowledge from other speech processing tasks where large-scale corpora are easily available, typically text-to-speech (TTS) and automatic speech recognition (ASR) We argue that VC models with such pretrained ASR or TTS model parameters can generate effective hidden representations for high-fidelity, highly intelligible converted speech.
  arXiv  Detail & Related papers  (2020-08-07T11:02:07Z)
• Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement [31.33429812278942]
  The proposed end-to-end speech synthesis model uses both speaker embedding and noise representation as conditional inputs to model speaker and noise information respectively. Experimental results show that the speech generated by the proposed approach has better subjective evaluation results than the method directly fine-tuning multi-speaker speech synthesis model.
  arXiv  Detail & Related papers  (2020-05-26T06:14:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.