Related papers: Fast, Not Fancy: Rethinking G2P with Rich Data and…

End-to-end (E2E) systems are fast replacing the conventional systems in the domain of automatic speech recognition. As the target labels are learned directly from speech data, the E2E systems need a bigger corpus for effective training. In…

In this paper, we address the limitations of existing text-to-image diffusion models in generating demographically fair results when given human-related descriptions. These models often struggle to disentangle the target language context…

Homomorphic encryption is one of the main solutions for building secure and privacy-preserving solutions for Machine Learning as a Service. This motivates the development of homomorphic algorithms for the main building blocks of AI,…

Homographs, words with different meanings but the same surface form, have long caused difficulty for machine translation systems, as it is difficult to select the correct translation based on the context. However, with the advent of neural…

Training massive-scale deep learning models on datasets spanning tens of terabytes presents critical challenges in hardware utilization and training reproducibility. In this paper, we identify and resolve profound data-loading bottlenecks…

The task of converting text input into video content is becoming an important topic for synthetic media generation. Several methods have been proposed with some of them reaching close-to-natural performances in constrained tasks. In this…

The need for privacy-preserving analytics is higher than ever due to the severity of privacy risks and to comply with new privacy regulations leading to an amplified interest in privacy-preserving techniques that try to balance between…

Automatic dubbing, which generates a corresponding version of the input speech in another language, could be widely utilized in many real-world scenarios such as video and game localization. In addition to synthesizing the translated…

We show that an end-to-end deep learning approach can be used to recognize either English or Mandarin Chinese speech--two vastly different languages. Because it replaces entire pipelines of hand-engineered components with neural networks,…

Grapheme-to-phoneme (G2P) conversion is an indispensable part of the Chinese Mandarin text-to-speech (TTS) system, and the core of G2P conversion is to solve the problem of polyphone disambiguation, which is to pick up the correct…

The zero-shot scenario for speech generation aims at synthesizing a novel unseen voice with only one utterance of the target speaker. Although the challenges of adapting new voices in zero-shot scenario exist in both stages -- acoustic…

The lack of labeled second language (L2) speech data is a major challenge in designing mispronunciation detection models. We introduce SpeechBlender - a fine-grained data augmentation pipeline for generating mispronunciation errors to…

Low resource of parallel data is the key challenge of accent conversion(AC) problem in which both the pronunciation units and prosody pattern need to be converted. We propose a two-stage generative framework "convert-and-speak" in which the…

Recent research has shown that large language models pretrained using unsupervised approaches can achieve significant performance improvement on many downstream tasks. Typically when adapting these language models to downstream tasks, like…

In this paper, we focus on improving the performance of the text-dependent speaker verification system in the scenario of limited training data. The speaker verification system deep learning based text-dependent generally needs a large…

State-of-the-art English automatic speech recognition systems typically use phonetic rather than graphemic lexicons. Graphemic systems are known to perform less well for English as the mapping from the written form to the spoken form is…

Recent efforts in Spoken Dialogue Modeling aim to synthesize spoken dialogue without the need for direct transcription, thereby preserving the wealth of non-textual information inherent in speech. However, this approach faces a challenge…

Despite recent advances in generative modeling for text-to-speech synthesis, these models do not yet have the same fine-grained adjustability of pitch-conditioned deterministic models such as FastPitch and FastSpeech2. Pitch information is…

In neural text-to-speech (TTS), two-stage system or a cascade of separately learned models have shown synthesis quality close to human speech. For example, FastSpeech2 transforms an input text to a mel-spectrogram and then HiFi-GAN…

Heterogeneous computing is one of the most important computational solutions to meet rapidly increasing demands on system performance. It typically allows the main flow of applications to be executed on a CPU while the most computationally…