Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval

• URL: http://arxiv.org/abs/2411.00664v2
• Date: Mon, 04 Nov 2024 17:05:58 GMT
• Title: Optimizing Contextual Speech Recognition Using Vector Quantization for Efficient Retrieval
• Authors: Nikolaos Flemotomos, Roger Hsiao, Pawel Swietojanski, Takaaki Hori, Dogan Can, Xiaodan Zhuang,
• Abstract summary: The biasing mechanism is typically based on a cross-attention module between the audio and a catalogue of biasing entries. This work proposes an approximation to cross-attention scoring based on vector quantization. We show that retrieval based shortlisting allows the system to efficiently leverage biasing catalogues of several thousands of entries.
• Score: 18.333752341467083
• License:
• Abstract: Neural contextual biasing allows speech recognition models to leverage contextually relevant information, leading to improved transcription accuracy. However, the biasing mechanism is typically based on a cross-attention module between the audio and a catalogue of biasing entries, which means computational complexity can pose severe practical limitations on the size of the biasing catalogue and consequently on accuracy improvements. This work proposes an approximation to cross-attention scoring based on vector quantization and enables compute- and memory-efficient use of large biasing catalogues. We propose to use this technique jointly with a retrieval based contextual biasing approach. First, we use an efficient quantized retrieval module to shortlist biasing entries by grounding them on audio. Then we use retrieved entries for biasing. Since the proposed approach is agnostic to the biasing method, we investigate using full cross-attention, LLM prompting, and a combination of the two. We show that retrieval based shortlisting allows the system to efficiently leverage biasing catalogues of several thousands of entries, resulting in up to 71% relative error rate reduction in personal entity recognition. At the same time, the proposed approximation algorithm reduces compute time by 20% and memory usage by 85-95%, for lists of up to one million entries, when compared to standard dot-product cross-attention.

Related papers

• Beyond Levenshtein: Leveraging Multiple Algorithms for Robust Word Error Rate Computations And Granular Error Classifications [5.266869303483375]
  The Word Error Rate (WER) is the common measure of accuracy for Automatic Speech Recognition (ASR) We present a non-destructive, token-based approach using an extended Levenshtein distance algorithm to compute a robust WER. We also provide an exemplary analysis of derived use cases, such as a punctuation error rate, and a web application for interactive use and visualisation of our implementation.
  arXiv  Detail & Related papers  (2024-08-28T08:14:51Z)
• Contextualized Automatic Speech Recognition with Attention-Based Bias Phrase Boosted Beam Search [44.94458898538114]
  This paper proposes an attention-based contextual biasing method that can be customized using an editable phrase list. The proposed method can be trained effectively by combining a bias phrase index loss and special tokens to detect the bias phrases in the input speech data.
  arXiv  Detail & Related papers  (2024-01-19T01:36:07Z)
• Contextual Biasing with the Knuth-Morris-Pratt Matching Algorithm [45.42075576656938]
  Contextual biasing refers to the problem of biasing automatic speech recognition systems towards rare entities. We propose algorithms for contextual biasing based on the Knuth-Morris-Pratt algorithm for pattern matching.
  arXiv  Detail & Related papers  (2023-09-29T22:50:10Z)
• Incrementally-Computable Neural Networks: Efficient Inference for Dynamic Inputs [75.40636935415601]
  Deep learning often faces the challenge of efficiently processing dynamic inputs, such as sensor data or user inputs. We take an incremental computing approach, looking to reuse calculations as the inputs change. We apply this approach to the transformers architecture, creating an efficient incremental inference algorithm with complexity proportional to the fraction of modified inputs.
  arXiv  Detail & Related papers  (2023-07-27T16:30:27Z)
• Robust Acoustic and Semantic Contextual Biasing in Neural Transducers for Speech Recognition [14.744220870243932]
  We propose to use lightweight character representations to encode fine-grained pronunciation features to improve contextual biasing. We further integrate pretrained neural language model (NLM) based encoders to encode the utterance's semantic context. Experiments using a Conformer Transducer model on the Librispeech dataset show a 4.62% - 9.26% relative WER improvement on different biasing list sizes.
  arXiv  Detail & Related papers  (2023-05-09T08:51:44Z)
• Efficient k-NN Search with Cross-Encoders using Adaptive Multi-Round CUR Decomposition [77.4863142882136]
  Cross-encoder models are prohibitively expensive for direct k-nearest neighbor (k-NN) search. We propose ADACUR, a method that adaptively, iteratively, and efficiently minimizes the approximation error for the practically important top-k neighbors.
  arXiv  Detail & Related papers  (2023-05-04T17:01:17Z)
• End-to-end contextual asr based on posterior distribution adaptation for hybrid ctc/attention system [61.148549738631814]
  End-to-end (E2E) speech recognition architectures assemble all components of traditional speech recognition system into a single model. Although it simplifies ASR system, it introduces contextual ASR drawback: the E2E model has worse performance on utterances containing infrequent proper nouns. We propose to add a contextual bias attention (CBA) module to attention based encoder decoder (AED) model to improve its ability of recognizing the contextual phrases.
  arXiv  Detail & Related papers  (2022-02-18T03:26:02Z)
• Approximate Nearest Neighbor Search under Neural Similarity Metric for Large-Scale Recommendation [20.42993976179691]
  We propose a novel method to extend ANN search to arbitrary matching functions. Our main idea is to perform a greedy walk with a matching function in a similarity graph constructed from all items. The proposed method has been fully deployed in the Taobao display advertising platform and brings a considerable advertising revenue increase.
  arXiv  Detail & Related papers  (2022-02-14T07:55:57Z)
• Recall@k Surrogate Loss with Large Batches and Similarity Mixup [62.67458021725227]
  Direct optimization, by gradient descent, of an evaluation metric is not possible when it is non-differentiable. In this work, a differentiable surrogate loss for the recall is proposed. The proposed method achieves state-of-the-art results in several image retrieval benchmarks.
  arXiv  Detail & Related papers  (2021-08-25T11:09:11Z)
• Learning Optical Flow from a Few Matches [67.83633948984954]
  We show that the dense correlation volume representation is redundant and accurate flow estimation can be achieved with only a fraction of elements in it. Experiments show that our method can reduce computational cost and memory use significantly, while maintaining high accuracy.
  arXiv  Detail & Related papers  (2021-04-05T21:44:00Z)

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.