Streaming Joint Speech Recognition and Disfluency Detection

• URL: http://arxiv.org/abs/2211.08726v2
• Date: Thu, 11 May 2023 07:55:09 GMT
• Title: Streaming Joint Speech Recognition and Disfluency Detection
• Authors: Hayato Futami, Emiru Tsunoo, Kentaro Shibata, Yosuke Kashiwagi, Takao Okuda, Siddhant Arora, Shinji Watanabe
• Abstract summary: We propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors. We show that the proposed joint models outperformed a BERT-based pipeline approach in both accuracy and latency.
• Score: 30.018034246393725
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Disfluency detection has mainly been solved in a pipeline approach, as post-processing of speech recognition. In this study, we propose Transformer-based encoder-decoder models that jointly solve speech recognition and disfluency detection, which work in a streaming manner. Compared to pipeline approaches, the joint models can leverage acoustic information that makes disfluency detection robust to recognition errors and provide non-verbal clues. Moreover, joint modeling results in low-latency and lightweight inference. We investigate two joint model variants for streaming disfluency detection: a transcript-enriched model and a multi-task model. The transcript-enriched model is trained on text with special tags indicating the starting and ending points of the disfluent part. However, it has problems with latency and standard language model adaptation, which arise from the additional disfluency tags. We propose a multi-task model to solve such problems, which has two output layers at the Transformer decoder; one for speech recognition and the other for disfluency detection. It is modeled to be conditioned on the currently recognized token with an additional token-dependency mechanism. We show that the proposed joint models outperformed a BERT-based pipeline approach in both accuracy and latency, on both the Switchboard and the corpus of spontaneous Japanese.

Related papers

• Qifusion-Net: Layer-adapted Stream/Non-stream Model for End-to-End Multi-Accent Speech Recognition [1.0690007351232649]
  We propose a layer-adapted fusion (LAF) model, called Qifusion-Net, which does not require any prior knowledge about the target accent. Experiment results demonstrate that our proposed methods outperform the baseline with relative reductions of 22.1$%$ and 17.2$%$ in character error rate (CER) across multi accent test datasets.
  arXiv  Detail & Related papers  (2024-07-03T11:35:52Z)
• Large Language Models for Dysfluency Detection in Stuttered Speech [16.812800649507302]
  Accurately detecting dysfluencies in spoken language can help to improve the performance of automatic speech and language processing components. Inspired by the recent trend towards the deployment of large language models (LLMs) as universal learners and processors of non-lexical inputs, we approach the task of multi-label dysfluency detection as a language modeling problem. We present hypotheses candidates generated with an automatic speech recognition system and acoustic representations extracted from an audio encoder model to an LLM, and finetune the system to predict dysfluency labels on three datasets containing English and German stuttered speech.
  arXiv  Detail & Related papers  (2024-06-16T17:51:22Z)
• Cross-Modal Learning for Anomaly Detection in Complex Industrial Process: Methodology and Benchmark [19.376814754500625]
  Anomaly detection in complex industrial processes plays a pivotal role in ensuring efficient, stable, and secure operation. This paper proposes a cross-modal Transformer to facilitate anomaly detection by exploring the correlation between visual features (video) and process variables (current) in the context of the fused magnesium smelting process. We present a pioneering cross-modal benchmark of the fused magnesium smelting process, featuring synchronously acquired video and current data for over 2.2 million samples.
  arXiv  Detail & Related papers  (2024-06-13T11:40:06Z)
• DiffVein: A Unified Diffusion Network for Finger Vein Segmentation and Authentication [50.017055360261665]
  We introduce DiffVein, a unified diffusion model-based framework which simultaneously addresses vein segmentation and authentication tasks. For better feature interaction between these two branches, we introduce two specialized modules. In this way, our framework allows for a dynamic interplay between diffusion and segmentation embeddings.
  arXiv  Detail & Related papers  (2024-02-03T06:49:42Z)
• Robust Wake-Up Word Detection by Two-stage Multi-resolution Ensembles [48.208214762257136]
  It employs two models: a lightweight on-device model for real-time processing of the audio stream and a verification model on the server-side. To protect privacy, audio features are sent to the cloud instead of raw audio.
  arXiv  Detail & Related papers  (2023-10-17T16:22:18Z)
• DiffSED: Sound Event Detection with Denoising Diffusion [70.18051526555512]
  We reformulate the SED problem by taking a generative learning perspective. Specifically, we aim to generate sound temporal boundaries from noisy proposals in a denoising diffusion process. During training, our model learns to reverse the noising process by converting noisy latent queries to the groundtruth versions.
  arXiv  Detail & Related papers  (2023-08-14T17:29:41Z)
• Do You Remember? Overcoming Catastrophic Forgetting for Fake Audio Detection [54.20974251478516]
  We propose a continual learning algorithm for fake audio detection to overcome catastrophic forgetting. When fine-tuning a detection network, our approach adaptively computes the direction of weight modification according to the ratio of genuine utterances and fake utterances. Our method can easily be generalized to related fields, like speech emotion recognition.
  arXiv  Detail & Related papers  (2023-08-07T05:05:49Z)
• DOAD: Decoupled One Stage Action Detection Network [77.14883592642782]
  Localizing people and recognizing their actions from videos is a challenging task towards high-level video understanding. Existing methods are mostly two-stage based, with one stage for person bounding box generation and the other stage for action recognition. We present a decoupled one-stage network dubbed DOAD, to improve the efficiency for-temporal action detection.
  arXiv  Detail & Related papers  (2023-04-01T08:06:43Z)
• Streaming end-to-end multi-talker speech recognition [34.76106500736099]
  We propose the Streaming Unmixing and Recognition Transducer (SURT) for end-to-end multi-talker speech recognition. Our model employs the Recurrent Neural Network Transducer (RNN-T) as the backbone that can meet various latency constraints. Based on experiments on the publicly available LibriSpeechMix dataset, we show that HEAT can achieve better accuracy compared with PIT.
  arXiv  Detail & Related papers  (2020-11-26T06:28:04Z)
• End-to-End Speech Recognition and Disfluency Removal [15.910282983166024]
  This paper investigates the task of end-to-end speech recognition and disfluency removal. We show that end-to-end models do learn to directly generate fluent transcripts. We propose two new metrics that can be used for evaluating integrated ASR and disfluency models.
  arXiv  Detail & Related papers  (2020-09-22T03:11:37Z)
• Learning Noise-Aware Encoder-Decoder from Noisy Labels by Alternating Back-Propagation for Saliency Detection [54.98042023365694]
  We propose a noise-aware encoder-decoder framework to disentangle a clean saliency predictor from noisy training examples. The proposed model consists of two sub-models parameterized by neural networks.
  arXiv  Detail & Related papers  (2020-07-23T18:47:36Z)

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.