Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition

• URL: http://arxiv.org/abs/2106.04275v1
• Date: Tue, 8 Jun 2021 12:12:33 GMT
• Title: Raw Waveform Encoder with Multi-Scale Globally Attentive Locally Recurrent Networks for End-to-End Speech Recognition
• Authors: Max W. Y. Lam, Jun Wang, Chao Weng, Dan Su, Dong Yu
• Abstract summary: We propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours.
• Score: 45.858039215825656
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: End-to-end speech recognition generally uses hand-engineered acoustic features as input and excludes the feature extraction module from its joint optimization. To extract learnable and adaptive features and mitigate information loss, we propose a new encoder that adopts globally attentive locally recurrent (GALR) networks and directly takes raw waveform as input. We observe improved ASR performance and robustness by applying GALR on different window lengths to aggregate fine-grain temporal information into multi-scale acoustic features. Experiments are conducted on a benchmark dataset AISHELL-2 and two large-scale Mandarin speech corpus of 5,000 hours and 21,000 hours. With faster speed and comparable model size, our proposed multi-scale GALR waveform encoder achieved consistent character error rate reductions (CERRs) from 7.9% to 28.1% relative over strong baselines, including Conformer and TDNN-Conformer. In particular, our approach demonstrated notable robustness than the traditional handcrafted features and outperformed the baseline MFCC-based TDNN-Conformer model by a 15.2% CERR on a music-mixed real-world speech test set.

Related papers

• TIGER: Time-frequency Interleaved Gain Extraction and Reconstruction for Efficient Speech Separation [19.126525226518975]
  We propose a speech separation model with significantly reduced parameters and computational costs. TIGER leverages prior knowledge to divide frequency bands and compresses frequency information. We show that TIGER achieves performance surpassing state-of-the-art (SOTA) model TF-GridNet.
  arXiv  Detail & Related papers  (2024-10-02T12:21:06Z)
• Anatomy of Industrial Scale Multilingual ASR [13.491861238522421]
  This paper describes AssemblyAI's industrial-scale automatic speech recognition (ASR) system. Our system leverages a diverse training dataset comprising unsupervised (12.5M hours), supervised (188k hours), and pseudo-labeled (1.6M hours) data across four languages.
  arXiv  Detail & Related papers  (2024-04-15T14:48:43Z)
• Unified End-to-End Speech Recognition and Endpointing for Fast and Efficient Speech Systems [17.160006765475988]
  We propose a method to jointly train the ASR and EP tasks in a single end-to-end (E2E) model. We introduce a "switch" connection, which trains the EP to consume either the audio frames directly or low-level latent representations from the ASR model. This results in a single E2E model that can be used during inference to perform frame filtering at low cost.
  arXiv  Detail & Related papers  (2022-11-01T23:43:15Z)
• CMGAN: Conformer-based Metric GAN for Speech Enhancement [6.480967714783858]
  We propose a conformer-based metric generative adversarial network (CMGAN) for time-frequency domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information. The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech.
  arXiv  Detail & Related papers  (2022-03-28T23:53:34Z)
• Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition [57.15942628305797]
  Articulatory features are invariant to acoustic signal distortion and have been successfully incorporated into automatic speech recognition systems for normal speech. This paper presents a cross-domain acoustic-to-articulatory (A2A) inversion approach that utilizes the parallel acoustic-articulatory data of the 15-hour TORGO corpus in model training. Cross-domain adapted to the 102.7-hour UASpeech corpus and to produce articulatory features.
  arXiv  Detail & Related papers  (2022-03-19T08:47:18Z)
• On Addressing Practical Challenges for RNN-Transduce [72.72132048437751]
  We adapt a well-trained RNN-T model to a new domain without collecting the audio data. We obtain word-level confidence scores by utilizing several types of features calculated during decoding. The proposed time stamping method can get less than 50ms word timing difference on average.
  arXiv  Detail & Related papers  (2021-04-27T23:31:43Z)
• WNARS: WFST based Non-autoregressive Streaming End-to-End Speech Recognition [59.975078145303605]
  We propose a novel framework, namely WNARS, using hybrid CTC-attention AED models and weighted finite-state transducers. On the AISHELL-1 task, our WNARS achieves a character error rate of 5.22% with 640ms latency, to the best of our knowledge, which is the state-of-the-art performance for online ASR.
  arXiv  Detail & Related papers  (2021-04-08T07:56:03Z)
• End-to-End Multi-speaker Speech Recognition with Transformer [88.22355110349933]
  We replace the RNN-based encoder-decoder in the speech recognition model with a Transformer architecture. We also modify the self-attention component to be restricted to a segment rather than the whole sequence in order to reduce computation.
  arXiv  Detail & Related papers  (2020-02-10T16:29:26Z)
• Temporal-Spatial Neural Filter: Direction Informed End-to-End Multi-channel Target Speech Separation [66.46123655365113]
  Target speech separation refers to extracting the target speaker's speech from mixed signals. Two main challenges are the complex acoustic environment and the real-time processing requirement. We propose a temporal-spatial neural filter, which directly estimates the target speech waveform from multi-speaker mixture.
  arXiv  Detail & Related papers  (2020-01-02T11:12:50Z)

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.