Related papers: Decision Making Based on Cohort Scores for Speaker…
The classification problem is a significant topic in machine learning which aims to teach machines how to group together data by particular criteria. In this paper, a framework for the ensemble learning (EL) method based on group decision…
Currently, the most widely used approach for speaker verification is the deep speaker embedding learning. In this approach, we obtain a speaker embedding vector by pooling single-scale features that are extracted from the last layer of a…
Building scalable and reusable multi-agent decision policies from offline datasets remains a challenge in offline multi-agent reinforcement learning (MARL), as existing methods often rely on fixed observation formats and action spaces that…
Persona-based dialogue generation is an important milestone towards building conversational artificial intelligence. Despite the ever-improving capabilities of large language models (LLMs), effectively integrating persona fidelity in…
The modeling of speech production often relies on a source-filter approach. Although methods parameterizing the filter have nowadays reached a certain maturity, there is still a lot to be gained for several speech processing applications in…
Phone-level pronunciation scoring is a challenging task, with performance far from that of human annotators. Standard systems generate a score for each phone in a phrase using models trained for automatic speech recognition (ASR) with…
Reverberation is present in our workplaces, our homes, concert halls and theatres. This paper investigates how deep learning can use the effect of reverberation on speech to classify a recording in terms of the room in which it was…
Keyword spotting systems often struggle to generalize to a diverse population with various accents and age groups. To address this challenge, we propose a novel approach that integrates speaker information into keyword spotting using…
LSTM-based speaker verification usually uses a fixed-length local segment randomly truncated from an utterance to learn the utterance-level speaker embedding, while using the average embedding of all segments of a test utterance to verify…
Multi-speaker speech synthesis is a technique for modeling multiple speakers' voices with a single model. Although many approaches using deep neural networks (DNNs) have been proposed, DNNs are prone to overfitting when the amount of…
Recent developments in speech synthesis have produced systems capable of outcome intelligible speech, but now researchers strive to create models that more accurately mimic human voices. One such development is the incorporation of multiple…
Most state-of-the-art Deep Learning (DL) approaches for speaker recognition work on a short utterance level. Given the speech signal, these algorithms extract a sequence of speaker embeddings from short segments and those are averaged to…
While machine learning techniques are traditionally resource intensive, we are currently witnessing an increased interest in hardware and energy efficient approaches. This need for resource-efficient machine learning is primarily driven by…
The performance of speaker verification degrades significantly in adverse acoustic environments with strong reverberation and noise. To address this issue, this paper proposes a spatial-temporal graph convolutional network (GCN) method for…
In various work contexts, such as meeting scheduling, collaborating, and project planning, collective decision-making is essential but often challenging due to diverse individual preferences, varying work focuses, and power dynamics among…
Much of the success of multi-agent debates depends on carefully choosing the right parameters. The decision-making protocol stands out as it can highly impact final model answers, depending on how decisions are reached. Systematic…
Cluster analysis requires many decisions: the clustering method and the implied reference model, the number of clusters and, often, several hyper-parameters and algorithms' tunings. In practice, one produces several partitions, and a final…
We propose an algorithm to separate simultaneously speaking persons from each other, the "cocktail party problem", using a single microphone. Our approach involves a deep recurrent neural networks regression to a vector space that is…
Due to the superior modeling ability of deep neural network (DNN), it is widely used in voice activity detection (VAD). However, the performance may degrade if no sufficient data especially for practical data could be used for training,…
Evaluating the conversational abilities of large language models (LLMs) remains a challenging task. Current mainstream approaches primarily rely on the "LLM-as-a-judge" paradigm, where an LLM is prompted to serve as an evaluator to assess…