相关论文: Improved ASR for Under-Resourced Languages Through…

The quality of automatic speech recognition (ASR) is critical to Dialogue Systems as ASR errors propagate to and directly impact downstream tasks such as language understanding (LU). In this paper, we propose multi-task neural approaches to…

With approximately 7,000 languages spoken worldwide, current large language models (LLMs) support only a small subset. Prior research indicates LLMs can learn new languages for certain tasks without supervised data. We extend this…

Pre-trained models, especially self-supervised learning (SSL) models, have demonstrated impressive results in automatic speech recognition (ASR) task. While most applications of SSL models focus on leveraging continuous representations as…

Attention-based sequence-to-sequence modeling provides a powerful and elegant solution for applications that need to map one sequence to a different sequence. Its success heavily relies on the availability of large amounts of training data.…

Multilingual automatic speech recognition (ASR) systems mostly benefit low resource languages but suffer degradation in performance across several languages relative to their monolingual counterparts. Limited studies have focused on…

When only a limited amount of accented speech data is available, to promote multi-accent speech recognition performance, the conventional approach is accent-specific adaptation, which adapts the baseline model to multiple target accents…

The utilization of speech Self-Supervised Learning (SSL) models achieves impressive performance on Automatic Speech Recognition (ASR). However, in low-resource language ASR, they encounter the domain mismatch problem between pre-trained and…

Spoken language understanding (SLU) tasks involve diverse skills that probe the information extraction, classification and/or generation capabilities of models. In this setting, task-specific training data may not always be available. While…

With recent advancements in language technologies, humans are now speaking to devices. Increasing the reach of spoken language technologies requires building systems in local languages. A major bottleneck here are the underlying…

Self-Supervised Learning (SSL) has gained traction for its ability to learn rich representations with low labeling costs, applicable across diverse downstream tasks. However, assessing the downstream-task performance remains challenging due…

In this paper, we proposed to apply meta learning approach for low-resource automatic speech recognition (ASR). We formulated ASR for different languages as different tasks, and meta-learned the initialization parameters from many…

Automatic speech recognition (ASR) is a crucial tool for linguists aiming to perform a variety of language documentation tasks. However, modern ASR systems use data-hungry transformer architectures, rendering them generally unusable for…

Multilingual training has been shown to improve acoustic modeling performance by sharing and transferring knowledge in modeling different languages. Knowledge sharing is usually achieved by using common lower-level layers for different…

Acoustic word embeddings are fixed-dimensional representations of variable-length speech segments. In settings where unlabelled speech is the only available resource, such embeddings can be used in "zero-resource" speech search, indexing…

Training automatic speech recognition (ASR) systems requires large amounts of data in the target language in order to achieve good performance. Whereas large training corpora are readily available for languages like English, there exists a…

Recent work has shown that it is possible to train an $\textit{unsupervised}$ automatic speech recognition (ASR) system using only unpaired audio and text. Existing unsupervised ASR methods assume that no labeled data can be used for…

Training deep neural networks for automatic speech recognition (ASR) requires large amounts of transcribed speech. This becomes a bottleneck for training robust models for accented speech which typically contains high variability in…

Acoustic word embedding models map variable duration speech segments to fixed dimensional vectors, enabling efficient speech search and discovery. Previous work explored how embeddings can be obtained in zero-resource settings where no…

Speaker recognition models face challenges in multi-lingual settings due to the entanglement of linguistic information within speaker embeddings. The overlap between vocal traits such as accent, vocal anatomy, and a language's phonetic…

Spoken language understanding (SLU) is a task aiming to extract high-level semantics from spoken utterances. Previous works have investigated the use of speech self-supervised models and textual pre-trained models, which have shown…