Related papers: Semi-Supervised Model Training for Unbounded Conve…

Self-training and unsupervised pre-training have emerged as effective approaches to improve speech recognition systems using unlabeled data. However, it is not clear whether they learn similar patterns or if they can be effectively…

Large-scale training corpora have significantly improved the performance of ASR models. Unfortunately, due to the relative scarcity of data, Chinese accents and dialects remain a challenge for most ASR models. Recent advancements in…

Existing multi-channel continuous speech separation (CSS) models are heavily dependent on supervised data - either simulated data which causes data mismatch between the training and real-data testing, or the real transcribed overlapping…

In this paper, we present our progress in pretraining Czech monolingual audio transformers from a large dataset containing more than 80 thousand hours of unlabeled speech, and subsequently fine-tuning the model on automatic speech…

Automatic speech recognition (ASR) is crucial for human-machine interaction in diverse applications like conversational agents, industrial robotics, call center automation, and automated subtitling. However, developing high-performance ASR…

Self-supervised learning (SSL) based speech pre-training has attracted much attention for its capability of extracting rich representations learned from massive unlabeled data. On the other hand, the use of weakly-supervised data is less…

The audio data is increasing day by day throughout the globe with the increase of telephonic conversations, video conferences and voice messages. This research provides a mechanism for identifying a speaker in an audio file, based on the…

Recently, masked prediction pre-training has seen remarkable progress in self-supervised learning (SSL) for speech recognition. It usually requires a codebook obtained in an unsupervised way, making it less accurate and difficult to…

Training data cleaning is a new application for generative model-based speech restoration (SR). This paper introduces Miipher-2, an SR model designed for million-hour scale data, for training data cleaning for large-scale generative models…

Training Transformer-based models demands a large amount of data, while obtaining aligned and labelled data in multimodality is rather cost-demanding, especially for audio-visual speech recognition (AVSR). Thus it makes a lot of sense to…

The developments in transformer encoder-decoder architectures have led to significant breakthroughs in machine translation, Automatic Speech Recognition (ASR), and instruction-based chat machines, among other applications. The pre-trained…

Recent end-to-end Automatic Speech Recognition (ASR) systems demonstrated the ability to outperform conventional hybrid DNN/ HMM ASR. Aside from architectural improvements in those systems, those models grew in terms of depth, parameters…

Automatic speech recognition (ASR) has been widely researched with supervised approaches, while many low-resourced languages lack audio-text aligned data, and supervised methods cannot be applied on them. In this work, we propose a…

Obtaining large-scale human-labeled datasets to train acoustic representation models is a very challenging task. On the contrary, we can easily collect data with machine-generated labels. In this work, we propose to exploit…

Recent advances in speech-aware language models have coupled strong acoustic encoders with large language models, enabling systems that move beyond transcription to produce richer outputs. Among these, word-level timestamp prediction is…

Speech recognition models often obtain degraded performance when tested on speech with unseen accents. Domain-adversarial training (DAT) and multi-task learning (MTL) are two common approaches for building accent-robust ASR models. ASR…

We address the problem of speech act recognition (SAR) in asynchronous conversations (forums, emails). Unlike synchronous conversations (e.g., meetings, phone), asynchronous domains lack large labeled datasets to train an effective SAR…

Accurately detecting voiced intervals in speech signals is a critical step in pitch tracking and has numerous applications. While conventional signal processing methods and deep learning algorithms have been proposed for this task, their…

Attention-based encoder-decoder architectures such as Listen, Attend, and Spell (LAS), subsume the acoustic, pronunciation and language model components of a traditional automatic speech recognition (ASR) system into a single neural…

Speech data has rich acoustic and paralinguistic information with important cues for understanding a speaker's tone, emotion, and intent, yet traditional large language models such as BERT do not incorporate this information. There has been…