Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers

• URL: http://arxiv.org/abs/2502.05232v1
• Date: Thu, 06 Feb 2025 22:09:52 GMT
• Title: Aligner-Encoders: Self-Attention Transformers Can Be Self-Transducers
• Authors: Adam Stooke, Rohit Prabhavalkar, Khe Chai Sim, Pedro Moreno Mengibar,
• Abstract summary: We show that the transformer-based encoder adopted in recent years is capable of performing the alignment internally during the forward pass. This new phenomenon enables a simpler and more efficient model, the "Aligner-Encoder" We conduct experiments demonstrating performance remarkably close to the state of the art.
• Score: 14.91083492000769
• License:
• Abstract: Modern systems for automatic speech recognition, including the RNN-Transducer and Attention-based Encoder-Decoder (AED), are designed so that the encoder is not required to alter the time-position of information from the audio sequence into the embedding; alignment to the final text output is processed during decoding. We discover that the transformer-based encoder adopted in recent years is actually capable of performing the alignment internally during the forward pass, prior to decoding. This new phenomenon enables a simpler and more efficient model, the "Aligner-Encoder". To train it, we discard the dynamic programming of RNN-T in favor of the frame-wise cross-entropy loss of AED, while the decoder employs the lighter text-only recurrence of RNN-T without learned cross-attention -- it simply scans embedding frames in order from the beginning, producing one token each until predicting the end-of-message. We conduct experiments demonstrating performance remarkably close to the state of the art, including a special inference configuration enabling long-form recognition. In a representative comparison, we measure the total inference time for our model to be 2x faster than RNN-T and 16x faster than AED. Lastly, we find that the audio-text alignment is clearly visible in the self-attention weights of a certain layer, which could be said to perform "self-transduction".

Related papers

• The Conformer Encoder May Reverse the Time Dimension [53.9351497436903]
  We analyze the initial behavior of the decoder cross-attention mechanism and find that it encourages the Conformer encoder self-attention. We propose methods and ideas of how this flipping can be avoided and investigate a novel method to obtain label-frame-position alignments.
  arXiv  Detail & Related papers  (2024-10-01T13:39:05Z)
• Alignment-Free Training for Transducer-based Multi-Talker ASR [55.1234384771616]
  Multi-talker RNNT (MT-RNNT) aims to achieve recognition without relying on costly front-end source separation. We propose a novel alignment-free training scheme for the MT-RNNT (MT-RNNT-AFT) that adopts the standard RNNT architecture.
  arXiv  Detail & Related papers  (2024-09-30T13:58:11Z)
• Diffsound: Discrete Diffusion Model for Text-to-sound Generation [78.4128796899781]
  We propose a novel text-to-sound generation framework that consists of a text encoder, a Vector Quantized Variational Autoencoder (VQ-VAE), a decoder, and a vocoder. The framework first uses the decoder to transfer the text features extracted from the text encoder to a mel-spectrogram with the help of VQ-VAE, and then the vocoder is used to transform the generated mel-spectrogram into a waveform.
  arXiv  Detail & Related papers  (2022-07-20T15:41:47Z)
• Deliberation of Streaming RNN-Transducer by Non-autoregressive Decoding [21.978994865937786]
  The method performs a few refinement steps, where each step shares a transformer decoder that attends to both text features and audio features. We show that, conditioned on hypothesis alignments of a streaming RNN-T model, our method obtains significantly more accurate recognition results than the first-pass RNN-T.
  arXiv  Detail & Related papers  (2021-12-01T01:34:28Z)
• Fast-MD: Fast Multi-Decoder End-to-End Speech Translation with Non-Autoregressive Hidden Intermediates [59.678108707409606]
  We propose Fast-MD, a fast MD model that generates HI by non-autoregressive decoding based on connectionist temporal classification (CTC) outputs followed by an ASR decoder. Fast-MD achieved about 2x and 4x faster decoding speed than that of the na"ive MD model on GPU and CPU with comparable translation quality.
  arXiv  Detail & Related papers  (2021-09-27T05:21:30Z)
• Stacked Acoustic-and-Textual Encoding: Integrating the Pre-trained Models into Speech Translation Encoders [30.160261563657947]
  Speech-to-translation data is scarce; pre-training is promising in end-to-end Speech Translation. We propose a Stacked. Acoustic-and-Textual (SATE) method for speech translation. Our encoder begins with processing the acoustic sequence as usual, but later behaves more like an. MT encoder for a global representation of the input sequence.
  arXiv  Detail & Related papers  (2021-05-12T16:09:53Z)
• Cross-Thought for Sentence Encoder Pre-training [89.32270059777025]
  Cross-Thought is a novel approach to pre-training sequence encoder. We train a Transformer-based sequence encoder over a large set of short sequences. Experiments on question answering and textual entailment tasks demonstrate that our pre-trained encoder can outperform state-of-the-art encoders.
  arXiv  Detail & Related papers  (2020-10-07T21:02:41Z)
• Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss [14.755108017449295]
  We present an end-to-end speech recognition model with Transformer encoders that can be used in a streaming speech recognition system. Transformer computation blocks based on self-attention are used to encode both audio and label sequences independently. We present results on the LibriSpeech dataset showing that limiting the left context for self-attention makes decoding computationally tractable for streaming.
  arXiv  Detail & Related papers  (2020-02-07T00:04:04Z)
• Streaming automatic speech recognition with the transformer model [59.58318952000571]
  We propose a transformer based end-to-end ASR system for streaming ASR. We apply time-restricted self-attention for the encoder and triggered attention for the encoder-decoder attention mechanism. Our proposed streaming transformer architecture achieves 2.8% and 7.2% WER for the "clean" and "other" test data of LibriSpeech.
  arXiv  Detail & Related papers  (2020-01-08T18:58:02Z)

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.