Related papers: A comparative analysis between Conformer-Transduce…

We analyze the impact of speaker adaptation in end-to-end automatic speech recognition models based on transformers and wav2vec 2.0 under different noise conditions. By including speaker embeddings obtained from x-vector and ECAPA-TDNN…

Automatic reading diagnosis systems can benefit both teachers for more efficient scoring of reading exercises and students for accessing reading exercises with feedback more easily. However, there are limited studies on Automatic Speech…

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mechanisms, which are…

Self-supervised learning, such as with the wav2vec 2.0 framework significantly improves the accuracy of end-to-end automatic speech recognition (ASR). Wav2vec 2.0 has been applied to single-channel end-to-end ASR models. In this work, we…

As human-machine voice interfaces provide easy access to increasingly intelligent machines, many state-of-the-art automatic speech recognition (ASR) systems are proposed. However, commercial ASR systems usually have poor performance on…

Recently proposed self-supervised learning approaches have been successful for pre-training speech representation models. The utility of these learned representations has been observed empirically, but not much has been studied about the…

This paper explores applying the wav2vec2 framework to speaker recognition instead of speech recognition. We study the effectiveness of the pre-trained weights on the speaker recognition task, and how to pool the wav2vec2 output sequence…

Current ASR systems are mainly trained and evaluated at the utterance level. Long range cross utterance context can be incorporated. A key task is to derive a suitable compact representation of the most relevant history contexts. In…

Recent advances in self-supervised learning through contrastive training have shown that it is possible to learn a competitive speech recognition system with as little as 10 minutes of labeled data. However, these systems are…

Automated Speech Recognition shows superhuman performance for adult English speech on a range of benchmarks, but disappoints when fed children's speech. This has long sat in the way of child-robot interaction. Recent evolutions in…

Recently, self-supervised learning (SSL) from unlabelled speech data has gained increased attention in the automatic speech recognition (ASR) community. Typical SSL methods include autoregressive predictive coding (APC), Wav2vec2.0, and…

Recent work on self-supervised pre-training focus on leveraging large-scale unlabeled speech data to build robust end-to-end (E2E) acoustic models (AM) that can be later fine-tuned on downstream tasks e.g., automatic speech recognition…

We develop automatic speech recognition (ASR) systems for stories told by Afrikaans and isiXhosa preschool children. Oral narratives provide a way to assess children's language development before they learn to read. We consider a range of…

Self-supervised pre-training methods based on contrastive learning or regression tasks can utilize more unlabeled data to improve the performance of automatic speech recognition (ASR). However, the robustness impact of combining the two…

Conformer, a convolution-augmented Transformer variant, has become the de facto encoder architecture for speech processing due to its superior performance in various tasks, including automatic speech recognition (ASR), speech translation…

Automatic speech recognition (ASR) systems often falter while processing stuttering-related disfluencies -- such as involuntary blocks and word repetitions -- yielding inaccurate transcripts. A critical barrier to progress is the scarcity…

Automatic speech recognition (ASR) has gained remarkable successes thanks to recent advances of deep learning, but it usually degrades significantly under real-world noisy conditions. Recent works introduce speech enhancement (SE) as…

To address the issue of poor generalization ability in end-to-end speech recognition models within deep learning, this study proposes a new Conformer-based speech recognition model called "Conformer-R" that incorporates the R-drop…

Speech recognition is the technology that enables machines to interpret and process human speech, converting spoken language into text or commands. This technology is essential for applications such as virtual assistants, transcription…

The goal of self-supervised learning (SSL) for automatic speech recognition (ASR) is to learn good speech representations from a large amount of unlabeled speech for the downstream ASR task. However, most SSL frameworks do not consider…