Related papers: Fixing Errors of the Google Voice Recognizer throu…
We introduce a new tokenizer for language models that minimizes the average tokens per character, thereby reducing the number of tokens needed to represent text during training and to generate text during inference. Our method, which we…
Spelling irregularities, known now as spelling mistakes, have been found for several centuries. As humans, we are able to understand most of the misspelled words based on their location in the sentence, perceived pronunciation, and context.…
While the use of social robots for language teaching has been explored, there remains limited work on a task-specific synthesized voices for language teaching robots. Given that language is a verbal task, this gap may have severe…
The effects of adding pitch and voice quality features such as jitter and shimmer to a state-of-the-art CNN model for Automatic Speech Recognition are studied in this work. Pitch features have been previously used for improving classical…
We introduce a data-driven approach for enabling word-level timestamp prediction in the Canary model. Accurate timestamp information is crucial for a variety of downstream tasks such as speech content retrieval and timed subtitles. While…
The challenges facing speech recognition systems, such as variations in pronunciations, adverse audio conditions, and the scarcity of labeled data, emphasize the necessity for a post-processing step that corrects recurring errors. Previous…
The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been heavily criticized for their poor correlation to human perception and their inability to…
This paper investigates the application of GPT-3.5 for Grammatical Error Correction (GEC) in multiple languages in several settings: zero-shot GEC, fine-tuning for GEC, and using GPT-3.5 to re-rank correction hypotheses generated by other…
Confusing-words are commonly encountered in real-life keyword spotting applications, which causes severe degradation of performance due to complex spoken terms and various kinds of words that sound similar to the predefined keywords. To…
Classroom speech and lectures often contain named entities (NEs) such as names of people and special terminology. While automatic speech recognition (ASR) systems have achieved remarkable performance on general speech, the word error rate…
Recent studies have shown that frame-level deep speaker features can be derived from a deep neural network with the training target set to discriminate speakers by a short speech segment. By pooling the frame-level features, utterance-level…
In this paper, we propose a deep convolutional neural network-based acoustic word embedding system on code-switching query by example spoken term detection. Different from previous configurations, we combine audio data in two languages for…
At the present time, computers are employed to solve complex tasks and problems ranging from simple calculations to intensive digital image processing and intricate algorithmic optimization problems to computationally-demanding weather…
Existing approaches for grammatical error correction (GEC) largely rely on supervised learning with manually created GEC datasets. However, there has been little focus on verifying and ensuring the quality of the datasets, and on how…
One of the most challenging scenarios for smart speakers is multi-talker, when target speech from the desired speaker is mixed with interfering speech from one or more speakers. A smart assistant needs to determine which voice to recognize…
When reading lips, many people benefit from additional visual information from the lip movements of the speaker, which is, however, very error prone. Algorithms for lip reading with artificial intelligence based on artificial neural…
In this paper, we focus on the task of small-footprint keyword spotting under the far-field scenario. Far-field environments are commonly encountered in real-life speech applications, causing severe degradation of performance due to room…
In this work, we propose a method to create domain-sensitive speech recognition models that utilize textual domain information by conditioning its generation on a given text prompt. This is accomplished by fine-tuning a pre-trained,…
Thanks to recent advances in deep learning, sophisticated generation tools exist, nowadays, that produce extremely realistic synthetic speech. However, malicious uses of such tools are possible and likely, posing a serious threat to our…
Word segmentation is the task of inserting or deleting word boundary characters in order to separate character sequences that correspond to words in some language. In this article we propose an approach based on a beam search algorithm and…