Related papers: Evaluating Automatic Speech Recognition in an Incr…

Optimization of modern ASR architectures is among the highest priority tasks since it saves many computational resources for model training and inference. The work proposes a new Uconv-Conformer architecture based on the standard Conformer…

In this paper, we describe recent performance improvements to the production Marchex speech recognition system for our spontaneous customer-to-business telephone conversations. In our previous work, we focused on in-domain language and…

Recently, Transformer-based architectures have been explored for speaker embedding extraction. Although the Transformer employs the self-attention mechanism to efficiently model the global interaction between token embeddings, it is…

We present the recent advances along with an error analysis of the IBM speaker recognition system for conversational speech. Some of the key advancements that contribute to our system include: a nearest-neighbor discriminant analysis (NDA)…

Speech emotion recognition (SER) has made significant strides with the advent of powerful self-supervised learning (SSL) models. However, the generalization of these models to diverse languages and emotional expressions remains a challenge.…

Transformer-based models have demonstrated their effectiveness in automatic speech recognition (ASR) tasks and even shown superior performance over the conventional hybrid framework. The main idea of Transformers is to capture the…

Blockwise self-attentional encoder models have recently emerged as one promising end-to-end approach to simultaneous speech translation. These models employ a blockwise beam search with hypothesis reliability scoring to determine when to…

We enhance the vanilla adversarial training method for unsupervised Automatic Speech Recognition (ASR) by a diffusion-GAN. Our model (1) injects instance noises of various intensities to the generator's output and unlabeled reference text…

While the use of deep neural networks has significantly boosted speaker recognition performance, it is still challenging to separate speakers in poor acoustic environments. To improve robustness of speaker recognition system performance in…

In recent years, neural models trained on large multilingual text and speech datasets have shown great potential for supporting low-resource languages. This study investigates the performances of two state-of-the-art Automatic Speech…

Flattery is an important aspect of human communication that facilitates social bonding, shapes perceptions, and influences behavior through strategic compliments and praise, leveraging the power of speech to build rapport effectively. Its…

Traditionally, research in automated speech recognition has focused on local-first encoding of audio representations to predict the spoken phonemes in an utterance. Unfortunately, approaches relying on such hyper-local information tend to…

The recently proposed Sequence-to-Sequence (seq2seq) framework advocates replacing complex data processing pipelines, such as an entire automatic speech recognition system, with a single neural network trained in an end-to-end fashion. In…

The efficacy of external language model (LM) integration with existing end-to-end (E2E) automatic speech recognition (ASR) systems can be improved significantly using the internal language model estimation (ILME) method. In this method, the…

We investigate robustness properties of pre-trained neural models for automatic speech recognition. Real life data in machine learning is usually very noisy and almost never clean, which can be attributed to various factors depending on the…

In recent years, speaker recognition systems based on raw waveform inputs have received increasing attention. However, the performance of such systems are typically inferior to the state-of-the-art handcrafted feature-based counterparts,…

Many studies have examined the shortcomings of word error rate (WER) as an evaluation metric for automatic speech recognition (ASR) systems. Since WER considers only literal word-level correctness, new evaluation metrics based on semantic…

Deploying high-quality automatic speech recognition (ASR) on edge devices requires models that jointly optimize accuracy, latency, and memory footprint while operating entirely on CPU without GPU acceleration. We conduct a systematic…

While integrating speech encoder with LLM requires substantial data and resources, use cases face limitations due to insufficient availability. To address this, we propose a solution with a parameter-efficient adapter that converts speech…

End-to-end (E2E) models, which directly predict output character sequences given input speech, are good candidates for on-device speech recognition. E2E models, however, present numerous challenges: In order to be truly useful, such models…