Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding

• URL: http://arxiv.org/abs/2603.20246v1
• Date: Tue, 10 Mar 2026 11:46:14 GMT
• Title: Decoding the decoder: Contextual sequence-to-sequence modeling for intracortical speech decoding
• Abstract summary: Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output.<n>It remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability.<n>We evaluate a Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Speech brain--computer interfaces require decoders that translate intracortical activity into linguistic output while remaining robust to limited data and day-to-day variability. While prior high-performing systems have largely relied on framewise phoneme decoding combined with downstream language models, it remains unclear what contextual sequence-to-sequence decoding contributes to sublexical neural readout, robustness, and interpretability. We evaluated a multitask Transformer-based sequence-to-sequence model for attempted speech decoding from area 6v intracortical recordings. The model jointly predicts phoneme sequences, word sequences, and auxiliary acoustic features. To address day-to-day nonstationarity, we introduced the Neural Hammer Scalpel (NHS) calibration module, which combines global alignment with feature-wise modulation. We further analyzed held-out-day generalization and attention patterns in the encoder and decoders. On the Willett et al. dataset, the proposed model achieved a state-of-the-art phoneme error rate of 14.3%. Word decoding reached 25.6% WER with direct decoding and 19.4% WER with candidate generation and rescoring. NHS substantially improved both phoneme and word decoding relative to linear or no day-specific transform, while held-out-day experiments showed increasing degradation on unseen days with temporal distance. Attention visualizations revealed recurring temporal chunking in encoder representations and distinct use of these segments by phoneme and word decoders. These results indicate that contextual sequence-to-sequence modeling can improve the fidelity of neural-to-phoneme readout from intracortical speech signals and suggest that attention-based analyses can generate useful hypotheses about how neural speech evidence is segmented and accumulated over time.

Related papers

• End-to-End Intracortical Speech Decoding from Neural Activity [0.8209843760716958]
  We propose an end-to-end Conformer-based neural decoder trained directly on intracortical recordings from a participant with ALS.<n>Without any external language model, the system achieves a character error rate (CER) of 23.80% on held-out validation data.
  arXiv  Detail & Related papers  (2026-05-23T00:39:59Z)
• Neural Decoding of Overt Speech from ECoG Using Vision Transformers and Contrastive Representation Learning [1.58476321728042]
  Speech Brain Computer Interfaces offer promising solutions to people with severe paralysis unable to communicate.<n>Recent studies have demonstrated convincing reconstruction of intelligible speech from surface electrocorticographic (ECoG) or intracortical recordings.<n>We present an offline speech decoding pipeline based on an encoder-decoder deep neural architecture, integrating Vision Transformers and contrastive learning.
  arXiv  Detail & Related papers  (2025-12-04T09:47:15Z)
• A Multimodal Seq2Seq Transformer for Predicting Brain Responses to Naturalistic Stimuli [0.0]
  The Algonauts 2025 Challenge called on the community to develop encoding models that predict whole-brain fMRI responses to naturalistic multimodal movies.<n>We propose a sequence-to-sequence Transformer that autoregressively predicts fMRI activity from visual, auditory, and language inputs.
  arXiv  Detail & Related papers  (2025-07-24T05:29:37Z)
• Decoding Phone Pairs from MEG Signals Across Speech Modalities [0.4054486015338004]
  We investigated magnetoencephalography signals to decode phones from brain activity during speech production and perception tasks.<n>Our results demonstrate significantly higher decoding accuracy during speech production compared to passive listening and playback modalities.
  arXiv  Detail & Related papers  (2025-05-21T10:31:34Z)
• A multimodal LLM for the non-invasive decoding of spoken text from brain recordings [0.4187344935012482]
  We propose and end-to-end multimodal LLM for decoding spoken text from fMRI signals. The proposed architecture is founded on (i) an encoder derived from a specific transformer incorporating an augmented embedding layer for the encoder and a better-adjusted attention mechanism than that present in the state of the art. A benchmark in performed on a corpus consisting of a set of interactions human-human and human-robot interactions where fMRI and conversational signals are recorded synchronously.
  arXiv  Detail & Related papers  (2024-09-29T14:03:39Z)
• VQ-CTAP: Cross-Modal Fine-Grained Sequence Representation Learning for Speech Processing [81.32613443072441]
  For tasks such as text-to-speech (TTS), voice conversion (VC), and automatic speech recognition (ASR), a cross-modal fine-grained (frame-level) sequence representation is desired.<n>We propose a method called Quantized Contrastive Token-Acoustic Pre-training (VQ-CTAP), which uses the cross-modal sequence transcoder to bring text and speech into a joint space.
  arXiv  Detail & Related papers  (2024-08-11T12:24:23Z)
• CoLM-DSR: Leveraging Neural Codec Language Modeling for Multi-Modal Dysarthric Speech Reconstruction [61.067153685104394]
  Dysarthric speech reconstruction (DSR) aims to transform dysarthric speech into normal speech. It still suffers from low speaker similarity and poor prosody naturalness. We propose a multi-modal DSR model by leveraging neural language modeling to improve the reconstruction results.
  arXiv  Detail & Related papers  (2024-06-12T15:42:21Z)
• Minimally-Supervised Speech Synthesis with Conditional Diffusion Model and Language Model: A Comparative Study of Semantic Coding [57.42429912884543]
  We propose Diff-LM-Speech, Tetra-Diff-Speech and Tri-Diff-Speech to solve high dimensionality and waveform distortion problems. We also introduce a prompt encoder structure based on a variational autoencoder and a prosody bottleneck to improve prompt representation ability. Experimental results show that our proposed methods outperform baseline methods.
  arXiv  Detail & Related papers  (2023-07-28T11:20:23Z)
• 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)
• Pre-Training Transformer Decoder for End-to-End ASR Model with Unpaired Speech Data [145.95460945321253]
  We introduce two pre-training tasks for the encoder-decoder network using acoustic units, i.e., pseudo codes. The proposed Speech2C can relatively reduce the word error rate (WER) by 19.2% over the method without decoder pre-training.
  arXiv  Detail & Related papers  (2022-03-31T15:33:56Z)
• 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)
• Any-to-Many Voice Conversion with Location-Relative Sequence-to-Sequence Modeling [61.351967629600594]
  This paper proposes an any-to-many location-relative, sequence-to-sequence (seq2seq), non-parallel voice conversion approach. In this approach, we combine a bottle-neck feature extractor (BNE) with a seq2seq synthesis module. Objective and subjective evaluations show that the proposed any-to-many approach has superior voice conversion performance in terms of both naturalness and speaker similarity.
  arXiv  Detail & Related papers  (2020-09-06T13:01:06Z)
• Attentional Speech Recognition Models Misbehave on Out-of-domain Utterances [16.639133822656458]
  We decode audio from the British National Corpus with an attentional encoder-decoder model trained solely on the LibriSpeech corpus. We observe that there are many 5-second recordings that produce more than 500 characters of decoding output. A frame-synchronous hybrid (DNN-HMM) model trained on the same data does not produce these unusually long transcripts.
  arXiv  Detail & Related papers  (2020-02-12T18:53:56Z)

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.