Search for: All records

We consider the problem of personalizing audio to maximize user experience. Briefly, we aim to find a filter h*, which applied to any music or speech, will maximize the user’s satisfaction. This is a black-box optimization problem since the user’s satisfaction function is unknown. Substantive work has been done on this topic where the key idea is to play audio samples to the user, each shaped by a different filter hi, and query the user for their satisfaction scores f(hi). A family of “surrogate” functions is then designed to fit these scores and the optimization method gradually refines these functions to arrive at the filter ˆh* that maximizes satisfaction. In certain applications, we observe that a second type of querying is possible where users can tell us the individual elements h*[j] of the optimal filter h*. Consider an analogy from cooking where the goal is to cook a recipe that maximizes user satisfaction. A user can be asked to score various cooked recipes (e.g., tofu fried rice) or to score individual ingredients (say, salt, sugar, rice, chicken, etc.). Given a budget of B queries, where a query can be of either type, our goal is to find the recipe that will maximize this user’s satisfaction. Our proposal builds on Sparse Gaussian Process Regression (GPR) and shows how a hybrid approach can outperform any one type of querying. Our results are validated through simulations and real world experiments, where volunteers gave feedback on music/speech audio and were able to achieve high satisfaction levels. We believe this idea of hybrid querying opens new problems in black-box optimization and solutions can benefit other applications beyond audio personalization. 

Voice assistants such as Amazon Echo (Alexa) and Google Home use microphone arrays to estimate the angle of arrival (AoA) of the human voice. This paper focuses on adding user localization as a new capability to voice assistants. For any voice command, we desire Alexa to be able to localize the user inside the home. The core challenge is two-fold: (1) accurately estimating the AoAs of multipath echoes without the knowledge of the source signal, and (2) tracing back these AoAs to reverse triangulate the user's location.We develop VoLoc, a system that proposes an iterative align-and-cancel algorithm for improved multipath AoA estimation, followed by an error-minimization technique to estimate the geometry of a nearby wall reflection. The AoAs and geometric parameters of the nearby wall are then fused to reveal the user's location. Under modest assumptions, we report localization accuracy of 0.44 m across different rooms, clutter, and user/microphone locations. VoLoc runs in near real-time but needs to hear around 15 voice commands before becoming operational.