Search Results for "paper"

StreamSpeech is an “all-in-one” speech model designed to perform offline and simultaneous speech recognition, speech translation, and speech synthesis within a single unified architecture. Developed as part of an ACL 2024 paper, it targets streaming and low-latency scenarios where intermediate results and final translations or synthetic speech must be produced continuously as audio is being received. The model supports eight tasks: offline ASR, speech-to-text translation, speech-to-speech translation, and TTS, as well as their streaming or simultaneous counterparts, all handled by the same underlying system. ...

Tacotron-2 is a TensorFlow implementation of DeepMind’s Tacotron-2 end-to-end text-to-speech architecture, which predicts mel spectrograms from raw text and then feeds them to a neural vocoder such as WaveNet. It reproduces the original paper’s hyperparameters exactly via paper_hparams.py, while also offering a tuned hparams.py with extra improvements that often yield better audio quality in practice. The repository is structured as a full training pipeline: dataset preparation,...

DC-TTS is a TensorFlow implementation of the DC-TTS architecture, a fully convolutional text-to-speech system designed to be efficiently trainable while producing natural speech. It follows the “Efficiently Trainable Text-to-Speech System Based on Deep Convolutional Networks with Guided Attention” paper, but the author adapts and extends the design to make it practical for real experiments. The model is split into two networks: Text2Mel, which maps text to mel-spectrograms, and SSRN (spectrogram super-resolution network), which converts low-resolution mel-spectrograms into high-resolution magnitude spectrograms suitable for waveform synthesis. ...