Caleb Rascón

Caleb Rascon

Real-time speech enhancement has began to rise in performance, and the Demucs Denoiser model has recently demonstrated strong performance in multiple-speech-source scenarios when accompanied by a location-based speech target selection strategy. However, it has shown to be sensitive to errors in the direction-of-arrival (DOA) estimation. In this work, a DOA correction scheme is proposed that uses the real-time estimated speech quality of its enhanced output as the observed variable in an Adam-based optimization feedback loop to find the correct DOA. In spite of the high variability of the speech quality estimation, the proposed system is able to correct in real-time an error of up to 15$^o$ using only the speech quality as its guide. Several insights are provided for future versions of the proposed system to speed up convergence and further reduce the speech quality estimation variability.

Ivette Velez, Caleb Rascon, Gibran Fuentes-Pineda

Verifying if two audio segments belong to the same speaker has been recently put forward as a flexible way to carry out speaker identification, since it does not require to be re-trained when new speakers appear on the auditory scene. Although many of the current techniques have achieved high performances, they require a considerably high amount of memory, and a specific minimum length for their input audio segments. These requirements limit the applicability of these techniques in scenarios such as service robots, internet of things and virtual assistants, where computational resources are limited and the users tend to speak in short segments. In this work we propose a BLSTM-based model that reaches a level of performance comparable to the current state of the art when using short input audio segments, while requiring a considerably less amount of memory. Further, as far as we know, a complete speaker identification system has not been reported using this verification paradigm. Thus, we present a complete online speaker identifier, based on a simple voting system, that shows that the proposed BLSTM-based model achieves a similar performance at identifying speakers online compared to the current state of the art.

Ivette Vélez, Caleb Rascon, Gibrán Fuentes-Pineda

In service robotics, there is an interest to identify the user by voice alone. However, in application scenarios where a service robot acts as a waiter or a store clerk, new users are expected to enter the environment frequently. Typically, speaker identification models need to be retrained when this occurs, which can take an impractical amount of time. In this paper, a new approach for speaker identification through verification has been developed using a Siamese Convolutional Neural Network architecture (SCNN), where it learns to generically verify if two audio signals are from the same speaker. By having an external database of recorded audio of the users, identification is carried out by verifying the speech input with each of its entries. If new users are encountered, it is only required to add their recorded audio to the external database to be able to be identified, without retraining. The system was evaluated in four different aspects: the performance of the verifier, the performance of the system as a classifier using clean audio, its speed, and its accuracy in real-life settings. Its performance in conjunction with its one-shot-learning capabilities, makes the proposed system a viable alternative for speaker identification for service robots.