Timestamped Embedding-Matching Acoustic-to-Word CTC ASR

• URL: http://arxiv.org/abs/2306.11473v1
• Date: Tue, 20 Jun 2023 11:53:43 GMT
• Title: Timestamped Embedding-Matching Acoustic-to-Word CTC ASR
• Authors: Woojay Jeon
• Abstract summary: We describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) The word timestamps enable the ASR to output word segmentations and word confusion networks without relying on a secondary model or forced alignment process when testing.
• Score: 2.842794675894731
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In this work, we describe a novel method of training an embedding-matching word-level connectionist temporal classification (CTC) automatic speech recognizer (ASR) such that it directly produces word start times and durations, required by many real-world applications, in addition to the transcription. The word timestamps enable the ASR to output word segmentations and word confusion networks without relying on a secondary model or forced alignment process when testing. Our proposed system has similar word segmentation accuracy as a hybrid DNN-HMM (Deep Neural Network-Hidden Markov Model) system, with less than 3ms difference in mean absolute error in word start times on TIMIT data. At the same time, we observed less than 5% relative increase in the word error rate compared to the non-timestamped system when using the same audio training data and nearly identical model size. We also contribute more rigorous analysis of multiple-hypothesis embedding-matching ASR in general.

Related papers

• On the Relevance of Phoneme Duration Variability of Synthesized Training Data for Automatic Speech Recognition [0.552480439325792]
  We focus on the temporal structure of synthetic data and its relation to ASR training. We show how much the degradation of synthetic data quality is influenced by duration modeling in non-autoregressive TTS. Using a simple algorithm we shift phoneme duration distributions of the TTS system closer to real durations.
  arXiv  Detail & Related papers  (2023-10-12T08:45:21Z)
• Extended Graph Temporal Classification for Multi-Speaker End-to-End ASR [77.82653227783447]
  We propose an extension of GTC to model the posteriors of both labels and label transitions by a neural network. As an example application, we use the extended GTC (GTC-e) for the multi-speaker speech recognition task.
  arXiv  Detail & Related papers  (2022-03-01T05:02:02Z)
• Sequence-level self-learning with multiple hypotheses [53.04725240411895]
  We develop new self-learning techniques with an attention-based sequence-to-sequence (seq2seq) model for automatic speech recognition (ASR) In contrast to conventional unsupervised learning approaches, we adopt the emphmulti-task learning (MTL) framework. Our experiment results show that our method can reduce the WER on the British speech data from 14.55% to 10.36% compared to the baseline model trained with the US English data only.
  arXiv  Detail & Related papers  (2021-12-10T20:47:58Z)
• Streaming End-to-End ASR based on Blockwise Non-Autoregressive Models [57.20432226304683]
  Non-autoregressive (NAR) modeling has gained more and more attention in speech processing. We propose a novel end-to-end streaming NAR speech recognition system. We show that the proposed method improves online ASR recognition in low latency conditions.
  arXiv  Detail & Related papers  (2021-07-20T11:42:26Z)
• 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)
• Hallucination of speech recognition errors with sequence to sequence learning [16.39332236910586]
  When plain text data is to be used to train systems for spoken language understanding or ASR, a proven strategy is to hallucinate what the ASR outputs would be given a gold transcription. We present novel end-to-end models to directly predict hallucinated ASR word sequence outputs, conditioning on an input word sequence as well as a corresponding phoneme sequence. This improves prior published results for recall of errors from an in-domain ASR system's transcription of unseen data, as well as an out-of-domain ASR system's transcriptions of audio from an unrelated task.
  arXiv  Detail & Related papers  (2021-03-23T02:09:39Z)
• A Correspondence Variational Autoencoder for Unsupervised Acoustic Word Embeddings [50.524054820564395]
  We propose a new unsupervised model for mapping a variable-duration speech segment to a fixed-dimensional representation. The resulting acoustic word embeddings can form the basis of search, discovery, and indexing systems for low- and zero-resource languages.
  arXiv  Detail & Related papers  (2020-12-03T19:24:42Z)
• Sequence-to-Sequence Learning via Attention Transfer for Incremental Speech Recognition [25.93405777713522]
  We investigate whether it is possible to employ the original architecture of attention-based ASR for ISR tasks. We design an alternative student network that, instead of using a thinner or a shallower model, keeps the original architecture of the teacher model but with shorter sequences. Our experiments show that by delaying the starting time of recognition process with about 1.7 sec, we can achieve comparable performance to one that needs to wait until the end.
  arXiv  Detail & Related papers  (2020-11-04T05:06:01Z)
• Emotion recognition by fusing time synchronous and time asynchronous representations [17.26466867595571]
  A novel two-branch neural network model structure is proposed for multimodal emotion recognition. It consists of a time synchronous branch (TSB) and a time asynchronous branch (TAB) The two-branch structure achieves state-of-the-art results in 4-way classification with all common test setups.
  arXiv  Detail & Related papers  (2020-10-27T07:14:31Z)
• Adapting End-to-End Speech Recognition for Readable Subtitles [15.525314212209562]
  In some use cases such as subtitling, verbatim transcription would reduce output readability given limited screen size and reading time. We first investigate a cascaded system, where an unsupervised compression model is used to post-edit the transcribed speech. Experiments show that with limited data far less than needed for training a model from scratch, we can adapt a Transformer-based ASR model to incorporate both transcription and compression capabilities.
  arXiv  Detail & Related papers  (2020-05-25T14:42:26Z)
• Wake Word Detection with Alignment-Free Lattice-Free MMI [66.12175350462263]
  Always-on spoken language interfaces, e.g. personal digital assistants, rely on a wake word to start processing spoken input. We present novel methods to train a hybrid DNN/HMM wake word detection system from partially labeled training data. We evaluate our methods on two real data sets, showing 50%--90% reduction in false rejection rates at pre-specified false alarm rates over the best previously published figures.
  arXiv  Detail & Related papers  (2020-05-17T19:22:25Z)

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.