Feature Joint-State Posterior Estimation in Factorial Speech Processing Models using Deep Neural Networks
This addresses a specific bottleneck in speech processing for applications like speech separation and recognition, though it appears incremental in nature.
The paper tackles the problem of calculating joint-state posteriors for mixed-audio features in factorial speech processing models, proposing a deep neural network method that achieves a 2.3% absolute performance improvement in monaural speech separation and recognition compared to the vector Taylor series method.
This paper proposes a new method for calculating joint-state posteriors of mixed-audio features using deep neural networks to be used in factorial speech processing models. The joint-state posterior information is required in factorial models to perform joint-decoding. The novelty of this work is its architecture which enables the network to infer joint-state posteriors from the pairs of state posteriors of stereo features. This paper defines an objective function to solve an underdetermined system of equations, which is used by the network for extracting joint-state posteriors. It develops the required expressions for fine-tuning the network in a unified way. The experiments compare the proposed network decoding results to those of the vector Taylor series method and show 2.3% absolute performance improvement in the monaural speech separation and recognition challenge. This achievement is substantial when we consider the simplicity of joint-state posterior extraction provided by deep neural networks.