A cost minimization approach to fix the vocabulary size in a tokenizer for an End-to-End ASR system
- URL: http://arxiv.org/abs/2406.02563v1
- Date: Mon, 29 Apr 2024 12:16:21 GMT
- Title: A cost minimization approach to fix the vocabulary size in a tokenizer for an End-to-End ASR system
- Authors: Sunil Kumar Kopparapu, Ashish Panda,
- Abstract summary: tokenization algorithms like Byte Pair Piece (BPE) and WordPiece are popular in identifying the tokens that are used in the overall training process of the speech recognition system.
We show through experiments on LibriSpeech 100 hour set that the performance of an end-to-end ASR system improves when the number of tokens are chosen carefully.
- Score: 10.70500939394669
- License: http://creativecommons.org/licenses/by/4.0/
- Abstract: Unlike hybrid speech recognition systems where the use of tokens was restricted to phones, biphones or triphones the choice of tokens in the end-to-end ASR systems is derived from the text corpus of the training data. The use of tokenization algorithms like Byte Pair Encoding (BPE) and WordPiece is popular in identifying the tokens that are used in the overall training process of the speech recognition system. Popular toolkits, like ESPNet use a pre-defined vocabulary size (number of tokens) for these tokenization algorithms, but there is no discussion on how vocabulary size was derived. In this paper, we build a cost function, assuming the tokenization process to be a black-box to enable choosing the number of tokens which might most benefit building an end-to-end ASR. We show through experiments on LibriSpeech 100 hour set that the performance of an end-to-end ASR system improves when the number of tokens are chosen carefully.
Related papers
- CosyVoice: A Scalable Multilingual Zero-shot Text-to-speech Synthesizer based on Supervised Semantic Tokens [49.569695524535454]
We propose to represent speech with supervised semantic tokens, which are derived from a multilingual speech recognition model by inserting vector quantization into the encoder.
Based on the tokens, we further propose a scalable zero-shot TTS synthesizer, CosyVoice, which consists of an LLM for text-to-token generation and a conditional flow matching model for token-to-speech synthesis.
arXiv Detail & Related papers (2024-07-07T15:16:19Z) - SEP: Self-Enhanced Prompt Tuning for Visual-Language Model [68.68025991850115]
We introduce a novel approach named Self-Enhanced Prompt Tuning (SEP)
SEP explicitly incorporates discriminative prior knowledge to enhance both textual-level and visual-level embeddings.
Comprehensive evaluations across various benchmarks and tasks confirm SEP's efficacy in prompt tuning.
arXiv Detail & Related papers (2024-05-24T13:35:56Z) - Tokenization Is More Than Compression [15.689084780238597]
Existing tokenization approaches like Byte-Pair.
(BPE) originate from the field of data compression, and it has been suggested that BPE stems from its ability to condense text into a relatively small number of tokens.
We test the hypothesis that fewer tokens lead to better downstream performance by introducing PathPiece, a new tokenizer that segments a document's text into the minimum number of tokens for a given vocabulary.
arXiv Detail & Related papers (2024-02-28T14:52:15Z) - Audio-to-Intent Using Acoustic-Textual Subword Representations from
End-to-End ASR [8.832255053182283]
We present a novel approach to predict the user's intent (the user speaking to the device or not) directly from acoustic and textual information encoded at subword tokens.
We show that our approach is highly accurate with correctly mitigating 93.3% of unintended user audio from invoking the smart assistant at 99% true positive rate.
arXiv Detail & Related papers (2022-10-21T17:45:00Z) - Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo
Languages [58.43299730989809]
We introduce Wav2Seq, the first self-supervised approach to pre-train both parts of encoder-decoder models for speech data.
We induce a pseudo language as a compact discrete representation, and formulate a self-supervised pseudo speech recognition task.
This process stands on its own, or can be applied as low-cost second-stage pre-training.
arXiv Detail & Related papers (2022-05-02T17:59:02Z) - Tree-constrained Pointer Generator for End-to-end Contextual Speech
Recognition [16.160767678589895]
TCPGen is proposed that incorporates such knowledge as a list of biasing words into both attention-based encoder-decoder and transducer end-to-end ASR models.
TCPGen structures the biasing words into an efficient prefix tree to serve as its symbolic input and creates a neural shortcut to facilitate recognising biasing words during decoding.
arXiv Detail & Related papers (2021-09-01T21:41:59Z) - Instant One-Shot Word-Learning for Context-Specific Neural
Sequence-to-Sequence Speech Recognition [62.997667081978825]
We present an end-to-end ASR system with a word/phrase memory and a mechanism to access this memory to recognize the words and phrases correctly.
In this paper we demonstrate that through this mechanism our system is able to recognize more than 85% of newly added words that it previously failed to recognize.
arXiv Detail & Related papers (2021-07-05T21:08:34Z) - Fast End-to-End Speech Recognition via a Non-Autoregressive Model and
Cross-Modal Knowledge Transferring from BERT [72.93855288283059]
We propose a non-autoregressive speech recognition model called LASO (Listen Attentively, and Spell Once)
The model consists of an encoder, a decoder, and a position dependent summarizer (PDS)
arXiv Detail & Related papers (2021-02-15T15:18:59Z) - Continuous speech separation: dataset and analysis [52.10378896407332]
In natural conversations, a speech signal is continuous, containing both overlapped and overlap-free components.
This paper describes a dataset and protocols for evaluating continuous speech separation algorithms.
arXiv Detail & Related papers (2020-01-30T18:01:31Z)
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.