A Calculus-Based Framework for Determining Vocabulary Size in End-to-End ASR

• URL: http://arxiv.org/abs/2605.14427v1
• Date: Thu, 14 May 2026 06:19:42 GMT
• Title: A Calculus-Based Framework for Determining Vocabulary Size in End-to-End ASR
• Abstract summary: In hybrid automatic speech recognition systems, the vocabulary size is determined by the number of phones, bi-phones, or tri-phones present in the language.<n>In contrast, end-to-end ASR systems derive their vocabulary, often referred to as tokens from the text corpus used for training.
• Score: 5.286244385413773
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: In hybrid automatic speech recognition (ASR) systems, the vocabulary size is unambiguous, typically determined by the number of phones, bi-phones, or tri-phones present in the language. In contrast, end-to-end ASR systems derive their vocabulary, often referred to as tokens from the text corpus used for training. The choice and, more importantly, the size of this vocabulary is a critical hyper-parameter in training end-to-end ASR systems. Tokenization algorithms such as Byte Pair Encoding (BPE), WordPiece, and Unigram Language Model (ULM) use the vocabulary size as an input hyper-parameter to generate the sub-words employed during ASR training. Popular toolkits like ESPNet provide a fixed vocabulary size in their training recipes, but there is little documentation or discussion in the literature regarding how these values are determined. Recent work [1] has formalized an approach to identify the vocabulary size best suited for end-to-end ASR, introducing a cost function framework that treats the tokenization process as a black box. In this paper, we build upon that foundation by curve fitting the training data and using the principle of first and second derivative tests in calculus to formally estimate the vocabulary size hyper-parameter. We demonstrate the utility and usefulness of our approach by applying it on a standard Librispeech corpus and show that the optimal choice of vocabulary size hyper-parameter improves the performance of the ASR. The main contribution of this paper in formalizing an approach to identify the vocabulary size best suited for training an end-to-end ASR system.

Related papers

• Syllabic-Structure Decoder for Automatic Speech Recognition in Vietnamese [8.447993256993428]
  We are motivated from the phonemic features of Vietnamese to propose a Syllabic-Structure Decoder for ASR.<n>Our approach explicitly captures the phonological composition of syllables, enabling the decoder to generate valid syllabic structures from a compact phonemic inventory.
  arXiv  Detail & Related papers  (2026-05-27T02:51:09Z)
• AdaptBPE: From General Purpose to Specialized Tokenizers [18.70903226766322]
  We propose a post-training adaptation strategy that selectively replaces low-utility tokens with more relevant ones based on their frequency in an adaptation corpus.<n>Our algorithm identifies the token inventory that most effectively encodes the adaptation corpus for a given target vocabulary size.<n>This method serves as a lightweight adaptation mechanism, akin to a vocabulary fine-tuning process, enabling optimized tokenization for specific domains or tasks.
  arXiv  Detail & Related papers  (2026-01-29T12:59:40Z)
• A cost minimization approach to fix the vocabulary size in a tokenizer for an End-to-End ASR system [10.70500939394669]
  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.
  arXiv  Detail & Related papers  (2024-04-29T12:16:21Z)
• A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching [60.51839859852572]
  We propose to resolve the text into multi concepts for multilingual semantic matching to liberate the model from the reliance on NER models. We conduct comprehensive experiments on English datasets QQP and MRPC, and Chinese dataset Medical-SM.
  arXiv  Detail & Related papers  (2024-03-05T13:55:16Z)
• 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)
• Short-Term Word-Learning in a Dynamically Changing Environment [63.025297637716534]
  We show how to supplement 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. We demonstrate significant improvements in the detection rate of new words with only a minor increase in false alarms.
  arXiv  Detail & Related papers  (2022-03-29T10:05:39Z)
• 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)
• 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)
• Grounded Compositional Outputs for Adaptive Language Modeling [59.02706635250856]
  A language model's vocabulary$-$typically selected before training and permanently fixed later$-$affects its size. We propose a fully compositional output embedding layer for language models. To our knowledge, the result is the first word-level language model with a size that does not depend on the training vocabulary.
  arXiv  Detail & Related papers  (2020-09-24T07:21:14Z)

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.