# Structured State Space Decoder for Speech Recognition and Synthesis

arXiv: https://arxiv.org/abs/2210.17098 · HTML: https://mlsanity.com/paper/2210.17098/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Speech and audio SSMs, one of 10 directions in State-space sequence models (S4, Mamba).
- Builds on 26 of its 36 references that are in the map.
- First posted on arXiv 31 Oct 2022.

## Placed in

- State-space sequence models (S4, Mamba) / [Speech and audio SSMs](https://mlsanity.com/ssm/speech-and-audio-ssms/)

## Builds on (most cited first, 26 of 26)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Layer Normalization](https://mlsanity.com/paper/1607.06450/) (2016)
- [Efficiently Modeling Long Sequences with Structured State Spaces](https://mlsanity.com/paper/2111.00396/) (2021)
- [Transformers are RNNs: Fast Autoregressive Transformers with Linear Attention](https://mlsanity.com/paper/2006.16236/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Transformer-XL: Attentive Language Models Beyond a Fixed-Length Context](https://mlsanity.com/paper/1901.02860/) (2019)
- [Big Bird: Transformers for Longer Sequences](https://mlsanity.com/paper/2007.14062/) (2020)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis](https://mlsanity.com/paper/2010.05646/) (2020)
- [Self-Attention with Relative Position Representations](https://mlsanity.com/paper/1803.02155/) (2018)
- [Deep Networks with Stochastic Depth](https://mlsanity.com/paper/1603.09382/) (2016)
- [Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions](https://mlsanity.com/paper/1712.05884/) (2017)
- [Language Modeling with Gated Convolutional Networks](https://mlsanity.com/paper/1612.08083/) (2016)
- [Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layers](https://mlsanity.com/paper/2110.13985/) (2021)
- [ESPnet: End-to-End Speech Processing Toolkit](https://mlsanity.com/paper/1804.00015/) (2018)
- [Listen, Attend and Spell](https://mlsanity.com/paper/1508.01211/) (2015)
- [Transformer Transducer: A Streamable Speech Recognition Model with Transformer Encoders and RNN-T Loss](https://mlsanity.com/paper/2002.02562/) (2020)
- [A Comparative Study on Transformer vs RNN in Speech Applications](https://mlsanity.com/paper/1909.06317/) (2019)
- [It's Raw! Audio Generation with State-Space Models](https://mlsanity.com/paper/2202.09729/) (2022)
- [Recent Developments on ESPnet Toolkit Boosted by Conformer](https://mlsanity.com/paper/2010.13956/) (2020)
- [ContextNet: Improving Convolutional Neural Networks for Automatic Speech Recognition with Global Context](https://mlsanity.com/paper/2005.03191/) (2020)
- [Branchformer: Parallel MLP-Attention Architectures to Capture Local and Global Context for Speech Recognition and Understanding](https://mlsanity.com/paper/2207.02971/) (2022)
- [Robust Sequence-to-Sequence Acoustic Modeling with Stepwise Monotonic Attention for Neural TTS](https://mlsanity.com/paper/1906.00672/) (2019)
- [ESPnet2-TTS: Extending the Edge of TTS Research](https://mlsanity.com/paper/2110.07840/) (2021)
- [A Comparative Study on Neural Architectures and Training Methods for Japanese Speech Recognition](https://mlsanity.com/paper/2106.05111/) (2021)
- [SRU++: Pioneering Fast Recurrence with Attention for Speech Recognition](https://mlsanity.com/paper/2110.05571/) (2021)

## Built on by (most cited first, 11 of 11)

- [Zipformer: A faster and better encoder for automatic speech recognition](https://mlsanity.com/paper/2310.11230/) (2023)
- [Reproducing Whisper-Style Training Using an Open-Source Toolkit and Publicly Available Data](https://mlsanity.com/paper/2309.13876/) (2023)
- [FlashFFTConv: Efficient Convolutions for Long Sequences with Tensor Cores](https://mlsanity.com/paper/2311.05908/) (2023)
- [Exploring the Capability of Mamba in Speech Applications](https://mlsanity.com/paper/2406.16808/) (2024)
- [A Multi-dimensional Deep Structured State Space Approach to Speech Enhancement Using Small-footprint Models](https://mlsanity.com/paper/2306.00331/) (2023)
- [Mamba-based Decoder-Only Approach with Bidirectional Speech Modeling for Speech Recognition](https://mlsanity.com/paper/2411.06968/) (2024)
- [Augmenting conformers with structured state-space sequence models for online speech recognition](https://mlsanity.com/paper/2309.08551/) (2023)
- [Let SSMs be ConvNets: State-space Modeling with Optimal Tensor Contractions](https://mlsanity.com/paper/2501.13230/) (2025)
- [CNVSRC 2024: The Second Chinese Continuous Visual Speech Recognition Challenge](https://mlsanity.com/paper/2506.02010/) (2025)
- [MagpieTTS-LF: Inference-Time Long-Form Speech Generation Without Training on Long-Form data](https://mlsanity.com/paper/2606.18485/) (2026)
- [Accurate, fast, cheap: Choose three. Replacing Multi-Head-Attention with Bidirectional Recurrent Attention for Long-Form ASR](https://mlsanity.com/paper/2506.19761/) (2025)

## Abstract (arXiv)

Automatic speech recognition (ASR) systems developed in recent years have shown promising results with self-attention models (e.g., Transformer and Conformer), which are replacing conventional recurrent neural networks. Meanwhile, a structured state space model (S4) has been recently proposed, producing promising results for various long-sequence modeling tasks, including raw speech classification. The S4 model can be trained in parallel, same as the Transformer model. In this study, we applied S4 as a decoder for ASR and text-to-speech (TTS) tasks by comparing it with the Transformer decoder. For the ASR task, our experimental results demonstrate that the proposed model achieves a competitive word error rate (WER) of 1.88%/4.25% on LibriSpeech test-clean/test-other set and a character error rate (CER) of 3.80%/2.63%/2.98% on the CSJ eval1/eval2/eval3 set. Furthermore, the proposed model is more robust than the standard Transformer model, particularly for long-form speech on both the datasets. For the TTS task, the proposed method outperforms the Transformer baseline.