Information Retrieval Machine Learning Publications Speech Processing

Spoken Language Recognition

The objective of Spoken Language Identification (LID) is to recognize automatically the language spoken in an unknown speech signal. This system has several applications such as Speech-To-Speech Machine Translation Systems and telephone-based services. In the case of Automatic Speech Recognition (ASR), the LID allows the selection of appropriate parameters of the ASR system. There are two main types of LID system: there are LIDs based on spectral features and others based on tokens.

Read More
Audio Analysis Audio Fingerprint Information Retrieval Publications

Audio Fingerprint

An audio fingerprint is a kind of compact representation of an audio signal. It allows indentifying an unknown audio signal by trying to match its signature against the signature of the entire audio signal stored in a database. This system can be useful in detecting pirated audio signals (watermarking) or recognizing or identifying unknown music broadcast by a radio station, for example. Another purpose of the audio fingerprint is integrity verification.

Read More
Information Retrieval Machine Learning Publications Speech Recognition

Automatic Speech Recognition (ASR)

ASR aims to transcribe an unknown speech signal into text. This textual information can later be processed by a text mining system in order to spot essential keywords amongst the information provided by the input speech signal.

Read More
Publications Speech Processing

Noise Reduction

Noise Reduction is an important preprocessing step in any speech processing system. In so far as in speech recognition, acoustic models are generally obtained from clean speech signals, it must be recognized that preprocessing aims to clean a speech signal. We present here two of the most popular techniques: spectral subtraction and Wiener filter.

Read More
Information Retrieval Publications Text Mining

Text Mining for Information Retrieval

Text mining aims at determining the similarity between a given text and a set of documents stored in a given database. In Information Retrieval (IR), Text mining can be used to extract essential information in any textual query document.

Read More
Information Retrieval Publications Signal Processing Speech Processing Speech Recognition

Keyword Spotting

Keyword spotting (KWS) or Spoken Term Detection (SPT) is a subcategory of Automatic Speech Recognition (ASR). Contrarily to ASR whose objective is to transcribe a speech in its entirety, KWS must detect only a predefined set of words.

Read More
1 2 3