Related papers: Massively Multilingual Neural Grapheme-to-Phoneme …
Grapheme-to-phoneme (G2P) conversion serves as an essential component in Chinese Mandarin text-to-speech (TTS) system, where polyphone disambiguation is the core issue. In this paper, we propose an end-to-end framework to predict the…
End-to-end (E2E) automatic speech recognition (ASR) systems directly map acoustics to words using a unified model. Previous works mostly focus on E2E training a single model which integrates acoustic and language model into a whole.…
Transformer-based models have recently become very popular for sequence-to-sequence applications such as machine translation and speech recognition. This work proposes a dual-decoder transformer model for low-resource multilingual speech…
This paper describes AraS2P, our speech-to-phonemes system submitted to the Iqra'Eval 2025 Shared Task. We adapted Wav2Vec2-BERT via Two-Stage training strategy. In the first stage, task-adaptive continue pretraining was performed on…
Multi-agent systems powered by Large Language Models face a critical challenge: agents communicate through natural language, leading to semantic drift, hallucination propagation, and inefficient token consumption. We propose G2CP…
The research community has long studied computer-assisted pronunciation training (CAPT) methods in non-native speech. Researchers focused on studying various model architectures, such as Bayesian networks and deep learning methods, as well…
While neural networks have been employed to handle several different text-to-speech tasks, ours is the first system to use neural networks throughout, for both linguistic and acoustic processing. We divide the text-to-speech task into three…
To scale neural speech synthesis to various real-world languages, we present a multilingual end-to-end framework that maps byte inputs to spectrograms, thus allowing arbitrary input scripts. Besides strong results on 40+ languages, the…
Development of a proper names pronunciation lexicon is usually a manual effort which can not be avoided. Grapheme to phoneme (G2P) conversion modules, in literature, are usually rule based and work best for non-proper names in a particular…
Decoding attempted speech from neural activity offers a promising avenue for restoring communication abilities in individuals with speech impairments. Previous studies have focused on mapping neural activity to text using phonemes as the…
This paper presents our segmentation system developed for the MLP 2017 shared tasks on cross-lingual word segmentation and morpheme segmentation. We model both word and morpheme segmentation as character-level sequence labelling tasks. The…
Previous work on end-to-end translation from speech has primarily used frame-level features as speech representations, which creates longer, sparser sequences than text. We show that a naive method to create compressed phoneme-like speech…
Labeled audio data is insufficient to build satisfying speech recognition systems for most of the languages in the world. There have been some zero-resource methods trying to perform phoneme or word-level speech recognition without labeled…
Building language-universal speech recognition systems entails producing phonological units of spoken sound that can be shared across languages. While speech annotations at the language-specific phoneme or surface levels are readily…
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.…
Building multilingual and crosslingual models help bring different languages together in a language universal space. It allows models to share parameters and transfer knowledge across languages, enabling faster and better adaptation to a…
Text-to-speech conversion has traditionally been performed either by concatenating short samples of speech or by using rule-based systems to convert a phonetic representation of speech into an acoustic representation, which is then…
To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and…
This paper presents a state-of-the-art model for transcribing speech in any language into the International Phonetic Alphabet (IPA). Transcription of spoken languages into IPA is an essential yet time-consuming process in language…
End-to-end models, particularly Tacotron-based ones, are currently a popular solution for text-to-speech synthesis. They allow the production of high-quality synthesized speech with little to no text preprocessing. Indeed, they can be…