Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification

• URL: http://arxiv.org/abs/2209.06058v1
• Date: Tue, 13 Sep 2022 15:10:41 GMT
• Title: Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification
• Authors: Chao Zhang, Bo Li, Tara Sainath, Trevor Strohman, Sepand Mavandadi, Shuo-yiin Chang, Parisa Haghani
• Abstract summary: We propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. Experimental results on a voice search dataset with 9 language locales shows that the proposed method achieves an average of 96.2% LID prediction accuracy and the same second-pass WER
• Score: 14.197869575012925
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Language identification is critical for many downstream tasks in automatic speech recognition (ASR), and is beneficial to integrate into multilingual end-to-end ASR as an additional task. In this paper, we propose to modify the structure of the cascaded-encoder-based recurrent neural network transducer (RNN-T) model by integrating a per-frame language identifier (LID) predictor. RNN-T with cascaded encoders can achieve streaming ASR with low latency using first-pass decoding with no right-context, and achieve lower word error rates (WERs) using second-pass decoding with longer right-context. By leveraging such differences in the right-contexts and a streaming implementation of statistics pooling, the proposed method can achieve accurate streaming LID prediction with little extra test-time cost. Experimental results on a voice search dataset with 9 language locales shows that the proposed method achieves an average of 96.2% LID prediction accuracy and the same second-pass WER as that obtained by including oracle LID in the input.

Related papers

• Leveraging Timestamp Information for Serialized Joint Streaming Recognition and Translation [51.399695200838586]
  We propose a streaming Transformer-Transducer (T-T) model able to jointly produce many-to-one and one-to-many transcription and translation using a single decoder. Experiments on it,es,de->en prove the effectiveness of our approach, enabling the generation of one-to-many joint outputs with a single decoder for the first time.
  arXiv  Detail & Related papers  (2023-10-23T11:00:27Z)
• Generative error correction for code-switching speech recognition using large language models [49.06203730433107]
  Code-switching (CS) speech refers to the phenomenon of mixing two or more languages within the same sentence. We propose to leverage large language models (LLMs) and lists of hypotheses generated by an ASR to address the CS problem.
  arXiv  Detail & Related papers  (2023-10-17T14:49:48Z)
• Token-Level Serialized Output Training for Joint Streaming ASR and ST Leveraging Textual Alignments [49.38965743465124]
  This paper introduces a streaming Transformer-Transducer that jointly generates automatic speech recognition (ASR) and speech translation (ST) outputs using a single decoder. Experiments in monolingual and multilingual settings demonstrate that our approach achieves the best quality-latency balance.
  arXiv  Detail & Related papers  (2023-07-07T02:26:18Z)
• LAMASSU: Streaming Language-Agnostic Multilingual Speech Recognition and Translation Using Neural Transducers [71.76680102779765]
  Automatic speech recognition (ASR) and speech translation (ST) can both use neural transducers as the model structure. We propose LAMASSU, a streaming language-agnostic multilingual speech recognition and translation model using neural transducers.
  arXiv  Detail & Related papers  (2022-11-05T04:03:55Z)
• Optimizing Bilingual Neural Transducer with Synthetic Code-switching Text Generation [10.650573361117669]
  Semi-supervised training and synthetic code-switched data can improve the bilingual ASR system on code-switching speech. Our final system achieves 25% mixed error rate (MER) on the ASCEND English/Mandarin code-switching test set.
  arXiv  Detail & Related papers  (2022-10-21T19:42:41Z)
• Is Attention always needed? A Case Study on Language Identification from Speech [1.162918464251504]
  The present study introduces convolutional recurrent neural network (CRNN) based LID. CRNN based LID is designed to operate on the Mel-frequency Cepstral Coefficient (MFCC) characteristics of audio samples. The LID model exhibits high-performance levels ranging from 97% to 100% for languages that are linguistically similar.
  arXiv  Detail & Related papers  (2021-10-05T16:38:57Z)
• 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)
• Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses [13.976935216584298]
  A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel. We propose an approach that learns and combines acoustic level representations with embeddings estimated on ASR hypotheses. To reduce the processing cost and latency, we exploit a streaming architecture to identify the spoken language early.
  arXiv  Detail & Related papers  (2020-06-01T04:08:55Z)
• Towards Relevance and Sequence Modeling in Language Recognition [39.547398348702025]
  We propose a neural network framework utilizing short-sequence information in language recognition. A new model is proposed for incorporating relevance in language recognition, where parts of speech data are weighted more based on their relevance for the language recognition task. Experiments are performed using the language recognition task in NIST LRE 2017 Challenge using clean, noisy and multi-speaker speech data.
  arXiv  Detail & Related papers  (2020-04-02T18:31:18Z)
• Rnn-transducer with language bias for end-to-end Mandarin-English code-switching speech recognition [58.105818353866354]
  We propose an improved recurrent neural network transducer (RNN-T) model with language bias to alleviate the problem. We use the language identities to bias the model to predict the CS points. This promotes the model to learn the language identity information directly from transcription, and no additional LID model is needed.
  arXiv  Detail & Related papers  (2020-02-19T12:01:33Z)

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.