Related papers: PCA/LDA Approach for Text-Independent Speaker Reco…

Speech language models (SpeechLMs) accept speech input and produce speech output, allowing for more natural human-computer interaction compared to text-based large language models (LLMs). Traditional approaches for developing SpeechLMs are…

Utilizing language models (LMs) without internal access is becoming an attractive paradigm in the field of NLP as many cutting-edge LMs are released through APIs and boast a massive scale. The de-facto method in this type of black-box…

Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…

The speech feature extraction has been a key focus in robust speech recognition research; it significantly affects the recognition performance. In this paper, we first study a set of different features extraction methods such as linear…

While speech-based depression detection methods that use speaker-identity features, such as speaker embeddings, are popular, they often compromise patient privacy. To address this issue, we propose a speaker disentanglement method that…

A novel text-independent speaker identification (SI) method is proposed. This method uses the Mel-frequency Cepstral coefficients (MFCCs) and the dynamic information among adjacent frames as feature sets to capture speaker's…

Attention-based models have recently shown great performance on a range of tasks, such as speech recognition, machine translation, and image captioning due to their ability to summarize relevant information that expands through the entire…

Facial recognition system is one of the major successes of Artificial intelligence and has been used a lot over the last years. But, images are not the only biometric present: audio is another possible biometric that can be used as an…

In this paper, we present a fast and reliable method based on PCA to select the number of dimensions for word embeddings. First, we train one embedding with a generous upper bound (e.g. 1,000) of dimensions. Then we transform the embeddings…

Voice assistants, such as Siri and Google Assistant, typically model audio and text separately, resulting in lost speech information and increased complexity. Recent efforts to address this with end-to-end Speech Large Language Models…

The Engineers' Salary Prediction Challenge requires classifying salary categories into three classes based on tabular data. The job description is represented as a 300-dimensional word embedding incorporated into the tabular features,…

Large Language Models (LLMs) are one of the most promising technologies for the next era of speech generation systems, due to their scalability and in-context learning capabilities. Nevertheless, they suffer from multiple stability issues…

This paper presents a novel framework for multi-talker automatic speech recognition without the need for auxiliary information. Serialized Output Training (SOT), a widely used approach, suffers from recognition errors due to speaker…

Probabilistic linear discriminant analysis (PLDA) has broad application in open-set verification tasks, such as speaker verification. A key concern for PLDA is that the model is too simple (linear Gaussian) to deal with complicated data;…

Spoken language change detection (LCD) refers to identifying the language transitions in a code-switched utterance. Similarly, identifying the speaker transitions in a multispeaker utterance is known as speaker change detection (SCD). Since…

The SdSv challenge Task 2 provided an opportunity to assess efficiency and robustness of modern text-independent speaker verification systems. But it also made it possible to test new approaches, capable of taking into account the main…

Neural codec language models, built on transformer architecture, have revolutionized text-to-speech (TTS) synthesis, excelling in voice cloning by treating it as a prefix continuation task. However, their limited context length hinders…

The state-of-art approach for speaker verification consists of a neural network based embedding extractor along with a backend generative model such as the Probabilistic Linear Discriminant Analysis (PLDA). In this work, we propose a neural…

Speech recognition and speaker identification are important for authentication and verification in security purpose, but they are difficult to achieve. Speaker identification methods can be divided into text-independent and text-dependent.…

In speaker-independent speech emotion recognition, the training and testing samples are collected from diverse speakers, leading to a multi-domain shift challenge across the feature distributions of data from different speakers.…