Deep Text-to-Speech System with Seq2Seq Model
This work addresses efficiency and complexity issues in speech synthesis for applications requiring faster deployment, but it is incremental as it builds on existing Seq2Seq methods.
The paper tackles the problem of slow training and complex architectures in neural text-to-speech systems by introducing modifications to Seq2Seq models, resulting in faster attention alignment and good audio quality with a smaller model size.
Recent trends in neural network based text-to-speech/speech synthesis pipelines have employed recurrent Seq2seq architectures that can synthesize realistic sounding speech directly from text characters. These systems however have complex architectures and takes a substantial amount of time to train. We introduce several modifications to these Seq2seq architectures that allow for faster training time, and also allows us to reduce the complexity of the model architecture at the same time. We show that our proposed model can achieve attention alignment much faster than previous architectures and that good audio quality can be achieved with a model that's much smaller in size. Sample audio available at https://soundcloud.com/gary-wang-23/sets/tts-samples-for-cmpt-419.