Investigating the Effects of Large-Scale Pseudo-Stereo Data and Different Speech Foundation Model on Dialogue Generative Spoken Language Model
This work addresses a data bottleneck for researchers in spoken dialogue modeling, enabling more effective training without requiring scarce stereo recordings.
The paper tackled the scarcity of stereo dialogue data for spoken dialogue modeling by developing a pipeline to convert single-channel data into pseudo-stereo data, expanding the training dataset from 2,000 to 17,600 hours, which improved model performance. It also explored the use of different speech foundation models for dialogue generation.
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 when speakers talk simultaneously, requiring stereo dialogue data with speakers recorded on separate channels, a notably scarce resource. To address this, we have developed an innovative pipeline capable of transforming single-channel dialogue data into pseudo-stereo data. This expanded our training dataset from a mere 2,000 to an impressive 17,600 hours, significantly enriching the diversity and quality of the training examples available. The inclusion of this pseudo-stereo data has proven to be effective in improving the performance of spoken dialogue language models. Additionally, we explored the use of discrete units of different speech foundation models for spoken dialogue generation.