Related papers: Simple and Effective Unsupervised Speech Translati…

Recently, sequence-to-sequence models with attention have been successfully applied in Text-to-speech (TTS). These models can generate near-human speech with a large accurately-transcribed speech corpus. However, preparing such a large…

Unsupervised learning of cross-lingual word embedding offers elegant matching of words across languages, but has fundamental limitations in translating sentences. In this paper, we propose simple yet effective methods to improve…

In this paper, we investigate self-supervised pre-training methods for document text recognition. Nowadays, large unlabeled datasets can be collected for many research tasks, including text recognition, but it is costly to annotate them.…

While many speakers of low-resource languages regularly code-switch between their languages and other regional languages or English, datasets of codeswitched speech are too small to train bespoke acoustic models from scratch or do language…

In this paper, we present a semi-supervised training technique using pseudo-labeling for end-to-end neural diarization (EEND). The EEND system has shown promising performance compared with traditional clustering-based methods, especially in…

Deep learning-based speech enhancement models achieve remarkable performance when test distributions match training conditions, but often degrade when deployed in unpredictable real-world environments with domain shifts. To address this…

Recent success of large-scale pre-trained language models crucially hinge on fine-tuning them on large amounts of labeled data for the downstream task, that are typically expensive to acquire. In this work, we study self-training as one of…

Despite recent availability of large transcribed Kinyarwanda speech data, achieving robust speech recognition for Kinyarwanda is still challenging. In this work, we show that using self-supervised pre-training, following a simple curriculum…

Keyword Spotting (KWS) models are becoming increasingly integrated into various systems, e.g. voice assistants. To achieve satisfactory performance, these models typically rely on a large amount of labelled data, limiting their applications…

Unsupervised speech recognition has shown great potential to make Automatic Speech Recognition (ASR) systems accessible to every language. However, existing methods still heavily rely on hand-crafted pre-processing. Similar to the trend of…

Self-supervised pre-training has been successful in both text and speech processing. Speech and text offer different but complementary information. The question is whether we are able to perform a speech-text joint pre-training on unpaired…

Benefiting from the development of deep learning, text-to-speech (TTS) techniques using clean speech have achieved significant performance improvements. The data collected from real scenes often contains noise and generally needs to be…

Phoneme-level computer-assisted pronunciation training systems typically rely on phoneme-level annotations, which are costly and scarce. In this work, we investigate whether phoneme-level mispronunciation information can be learned without…

Self-supervised learning, which learns by constructing artificial labels given only the input signals, has recently gained considerable attention for learning representations with unlabeled datasets, i.e., learning without any…

Pseudo-labelling is a popular technique in unsuper-vised domain adaptation for semantic segmentation. However, pseudo labels are noisy and inevitably have confirmation bias due to the discrepancy between source and target domains and…

We present a simple yet effective approach to build multilingual speech-to-text (ST) translation by efficient transfer learning from pretrained speech encoder and text decoder. Our key finding is that a minimalistic LNA (LayerNorm and…

Recent advancements in Self-Supervised Learning (SSL) have shown promising results in Speaker Verification (SV). However, narrowing the performance gap with supervised systems remains an ongoing challenge. Several studies have observed that…

Sentiment analysis is an important task in understanding social media content like customer reviews, Twitter and Facebook feeds etc. In multilingual communities around the world, a large amount of social media text is characterized by the…

Self-supervised learning (SSL) algorithms have emerged as powerful tools that can leverage large quantities of unlabeled audio data to pre-train robust representations that support strong performance on diverse downstream tasks. Up to now…

A central goal of unsupervised learning is to acquire representations from unlabeled data or experience that can be used for more effective learning of downstream tasks from modest amounts of labeled data. Many prior unsupervised learning…