# Task Oriented Dialogue as a Catalyst for Self-Supervised Automatic Speech Recognition

arXiv: https://arxiv.org/abs/2401.02417 · HTML: https://mlsanity.com/paper/2401.02417/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 4 Jan 2024.

## Builds on (most cited first, 25 of 25)

- [BERTScore: Evaluating Text Generation with BERT](https://mlsanity.com/paper/1904.09675/) (2019)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations](https://mlsanity.com/paper/2006.11477/) (2020)
- [Supervised Contrastive Learning](https://mlsanity.com/paper/2004.11362/) (2020)
- [Conformer: Convolution-augmented Transformer for Speech Recognition](https://mlsanity.com/paper/2005.08100/) (2020)
- [Common Voice: A Massively-Multilingual Speech Corpus](https://mlsanity.com/paper/1912.06670/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Recent Advances in Natural Language Processing via Large Pre-Trained Language Models: A Survey](https://mlsanity.com/paper/2111.01243/) (2021)
- [YourTTS: Towards Zero-Shot Multi-Speaker TTS and Zero-Shot Voice Conversion for everyone](https://mlsanity.com/paper/2112.02418/) (2021)
- [NeMo: a toolkit for building AI applications using Neural Modules](https://mlsanity.com/paper/1909.09577/) (2019)
- [Combined Scaling for Zero-shot Transfer Learning](https://mlsanity.com/paper/2111.10050/) (2021)
- [SpokenWOZ: A Large-Scale Speech-Text Benchmark for Spoken Task-Oriented Dialogue Agents](https://mlsanity.com/paper/2305.13040/) (2023)
- [Contextual Adapters for Personalized Speech Recognition in Neural Transducers](https://mlsanity.com/paper/2205.13660/) (2022)
- [SIMMC 2.0: A Task-oriented Dialog Dataset for Immersive Multimodal Conversations](https://mlsanity.com/paper/2104.08667/) (2021)
- [Context-Aware Transformer Transducer for Speech Recognition](https://mlsanity.com/paper/2111.03250/) (2021)
- ["How Robust r u?": Evaluating Task-Oriented Dialogue Systems on Spoken Conversations](https://mlsanity.com/paper/2109.13489/) (2021)
- [A Survey on Recent Advances and Challenges in Reinforcement Learning Methods for Task-Oriented Dialogue Policy Learning](https://mlsanity.com/paper/2202.13675/) (2022)
- [Dialog-context aware end-to-end speech recognition](https://mlsanity.com/paper/1808.02171/) (2018)
- [DUAL: Discrete Spoken Unit Adaptive Learning for Textless Spoken Question Answering](https://mlsanity.com/paper/2203.04911/) (2022)
- [Multi-Modal Pre-Training for Automated Speech Recognition](https://mlsanity.com/paper/2110.09890/) (2021)
- [A Unified Framework for Domain Adaptation using Metric Learning on Manifolds](https://mlsanity.com/paper/1804.10834/) (2018)
- [Content-Context Factorized Representations for Automated Speech Recognition](https://mlsanity.com/paper/2205.09872/) (2022)
- [Attentive Contextual Carryover for Multi-Turn End-to-End Spoken Language Understanding](https://mlsanity.com/paper/2112.06743/) (2021)
- [Using External Off-Policy Speech-To-Text Mappings in Contextual End-To-End Automated Speech Recognition](https://mlsanity.com/paper/2301.02736/) (2023)
- [Unified Modeling of Multi-Domain Multi-Device ASR Systems](https://mlsanity.com/paper/2205.06655/) (2022)

## Built on by (most cited first, 1 of 1)

- [An Efficient Self-Learning Framework For Interactive Spoken Dialog Systems](https://mlsanity.com/paper/2409.10515/) (2024)

## Abstract (arXiv)

While word error rates of automatic speech recognition (ASR) systems have consistently fallen, natural language understanding (NLU) applications built on top of ASR systems still attribute significant numbers of failures to low-quality speech recognition results. Existing assistant systems collect large numbers of these unsuccessful interactions, but these systems usually fail to learn from these interactions, even in an offline fashion. In this work, we introduce CLC: Contrastive Learning for Conversations, a family of methods for contrastive fine-tuning of models in a self-supervised fashion, making use of easily detectable artifacts in unsuccessful conversations with assistants. We demonstrate that our CLC family of approaches can improve the performance of ASR models on OD3, a new public large-scale semi-synthetic meta-dataset of audio task-oriented dialogues, by up to 19.2%. These gains transfer to real-world systems as well, where we show that CLC can help to improve performance by up to 6.7% over baselines. We make OD3 publicly available at https://github.com/amazon-science/amazon-od3 .