Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses

• URL: http://arxiv.org/abs/2006.00703v1
• Date: Mon, 1 Jun 2020 04:08:55 GMT
• Title: Streaming Language Identification using Combination of Acoustic Representations and ASR Hypotheses
• Authors: Chander Chandak, Zeynab Raeesy, Ariya Rastrow, Yuzong Liu, Xiangyang Huang, Siyu Wang, Dong Kwon Joo, Roland Maas
• Abstract summary: 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.
• Score: 13.976935216584298
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: This paper presents our modeling and architecture approaches for building a highly accurate low-latency language identification system to support multilingual spoken queries for voice assistants. A common approach to solve multilingual speech recognition is to run multiple monolingual ASR systems in parallel and rely on a language identification (LID) component that detects the input language. Conventionally, LID relies on acoustic only information to detect input language. We propose an approach that learns and combines acoustic level representations with embeddings estimated on ASR hypotheses resulting in up to 50% relative reduction of identification error rate, compared to a model that uses acoustic only features. Furthermore, to reduce the processing cost and latency, we exploit a streaming architecture to identify the spoken language early when the system reaches a predetermined confidence level, alleviating the need to run multiple ASR systems until the end of input query. The combined acoustic and text LID, coupled with our proposed streaming runtime architecture, results in an average of 1500ms early identification for more than 50% of utterances, with almost no degradation in accuracy. We also show improved results by adopting a semi-supervised learning (SSL) technique using the newly proposed model architecture as a teacher model.

Related papers

• Leveraging Language ID to Calculate Intermediate CTC Loss for Enhanced Code-Switching Speech Recognition [5.3545957730615905]
  We introduce language identification information into the middle layer of the ASR model's encoder. We aim to generate acoustic features that imply language distinctions in a more implicit way, reducing the model's confusion when dealing with language switching.
  arXiv  Detail & Related papers  (2023-12-15T07:46:35Z)
• Efficient Spoken Language Recognition via Multilabel Classification [53.662747523872305]
  We show that our models obtain competitive results while being orders of magnitude smaller and faster than current state-of-the-art methods. Our multilabel strategy is more robust to unseen non-target languages compared to multiclass classification.
  arXiv  Detail & Related papers  (2023-06-02T23:04:19Z)
• Adapting Multi-Lingual ASR Models for Handling Multiple Talkers [63.151811561972515]
  State-of-the-art large-scale universal speech models (USMs) show a decent automatic speech recognition (ASR) performance across multiple domains and languages. We propose an approach to adapt USMs for multi-talker ASR. We first develop an enhanced version of serialized output training to jointly perform multi-talker ASR and utterance timestamp prediction.
  arXiv  Detail & Related papers  (2023-05-30T05:05:52Z)
• From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition [50.93943755401025]
  We propose a new parameter-efficient learning framework based on neural model reprogramming for cross-lingual speech recognition. We design different auxiliary neural architectures focusing on learnable pre-trained feature enhancement. Our methods outperform existing ASR tuning architectures and their extension with self-supervised losses.
  arXiv  Detail & Related papers  (2023-01-19T02:37:56Z)
• Streaming End-to-End Multilingual Speech Recognition with Joint Language Identification [14.197869575012925]
  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
  arXiv  Detail & Related papers  (2022-09-13T15:10:41Z)
• ASR data augmentation in low-resource settings using cross-lingual multi-speaker TTS and cross-lingual voice conversion [49.617722668505834]
  We show that our approach permits the application of speech synthesis and voice conversion to improve ASR systems using only one target-language speaker during model training. It is possible to obtain promising ASR training results with our data augmentation method using only a single real speaker in a target language.
  arXiv  Detail & Related papers  (2022-03-29T11:55:30Z)
• 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)
• Dynamic Acoustic Unit Augmentation With BPE-Dropout for Low-Resource End-to-End Speech Recognition [62.94773371761236]
  We consider building an effective end-to-end ASR system in low-resource setups with a high OOV rate. We propose a method of dynamic acoustic unit augmentation based on the BPE-dropout technique. Our monolingual Turkish Conformer established a competitive result with 22.2% character error rate (CER) and 38.9% word error rate (WER)
  arXiv  Detail & Related papers  (2021-03-12T10:10:13Z)
• Streaming End-to-End Bilingual ASR Systems with Joint Language Identification [19.09014345299161]
  We introduce streaming, end-to-end, bilingual systems that perform both ASR and language identification. The proposed method is applied to two language pairs: English-Spanish as spoken in the United States, and English-Hindi as spoken in India.
  arXiv  Detail & Related papers  (2020-07-08T05:00:25Z)
• Meta-Transfer Learning for Code-Switched Speech Recognition [72.84247387728999]
  We propose a new learning method, meta-transfer learning, to transfer learn on a code-switched speech recognition system in a low-resource setting. Our model learns to recognize individual languages, and transfer them so as to better recognize mixed-language speech by conditioning the optimization on the code-switching data.
  arXiv  Detail & Related papers  (2020-04-29T14:27:19Z)
• 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)

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.