Speaker: Théo Mariotte Data and time: Feb 9, 2023, at 10:30 Abstract: Speaker diarization answers the question « Who spoke and when? » in an audio stream. Most diarization systems consist of two major steps: segmentation and clustering. The former is related to speakers activity and detects time borders in the signal. The latter groups segments featuring …
Category: Seminars
Jan 19
Transfer Learning for Abusive Language Detection
Speaker: Tulika Bose Data and time: Jan 19, 2023, at 10:30 Abstract: The proliferation of social media, despite its multitude of benefits, has led to the increased spread of abusive language. Deep learning models for detecting abusive language have displayed great levels of in-corpus performance but under-perform substantially outside the training distribution. Moreover, they require …
Nov 24
BinauRec: A dataset to test the influence of the use of room impulse responses on binaural speech enhancement
Speaker: Louis Delebecque Data and time: Nov 24, 2022, at 10:30 Abstract: Thanks to spatial information contained in reverberated signals, multichannel speech enhancement (SE) algorithms are able to outperform single-channel systems. Reverberated signals are often generated from simulations of room impulse responses (RIRs). However, the influence of such methods on SE quality has not been investigated …
Nov 03
Training speech emotion classifier without categorical annotations
Speaker: Meysam Shamsi Data and place: Nov 3, 2022, at 10:30 Abstract: Emotion recognition task can be treated as a classification using categorical labeling or regression modeling using dimensional description in continuous space. An investigation of the relation between these two representations will be presented, then a classification pipeline that uses only dimensional annotation will be …
Sep 29
Flexible parametric spatial audio processing and spatial acoustic scene analysis research, in Aalto and Tampere University, Finland.
Speaker: Archontis Politis Data and place: Sep 29, 2022, at 10:30 – Hybrid Abstract: Archontis Politis is a researcher on spatial audio technologies currently at Tampere University, Finland, and in close collaboration with Aalto University, Finland. This presentation summarizes work that the researcher has been involved in those two universities, mainly around two areas. The first …
Sep 22
Sound event detection for low power embedded systems
Speaker: Marie-Anne Lacroix Data and place: September 22, 2022, at 10:30 – Hybrid Abstract: Supervised sound event detection software implementations currently achieve high performance. This allows the development of real-world applications, especially for the growing up domain of the Internet of Objects (IoT). However, current performance is achieved at the cost of hard computational complexity and …
Jun 09
Time-frequency fading
Speaker: Marina Kreme Data and place: June 9, 2022, at 10:30 – Hybrid Abstract: We are interested in the problem of attenuating time-frequency regions, for example when a disturbance signal is well localized in the time-frequency plane. We approach this problem from the point of view of time-frequency filtering, by formulating the optimization problem in the signal …
May 19
On the impact of normalization strategies in unsupervised adversarial domain adaptation for acoustic scene classification
Speaker: Mauricio Michel Olvera Zambrano Data and place: May 19, 2022, at 10:30 – Hybrid Abstract: Acoustic scene classification systems face performance degradation when trained and tested on data recorded by different devices. Unsupervised domain adaptation methods have been studied to reduce the impact of this mismatch. While they do not assume the availability of labels at …
May 12
Multimodal speech animation
Speaker: Louis Abel Data and place: May 12, 2022, at 10:30 – Hybrid Abstract: Multimodal speech animation is the next step to speech synthesis, combining visuals with audio allows the creation of embodied conversational agent (ECA) which can convey more information than a classic text-to-speech approach, several works have been done in the team to progress in …
Apr 28
Expanding the training data for neural network based hate speech classification
Speaker: Ashwin Geet D’Sa Data and place: April 28, 2022, at 10:30 – Hybrid Abstract: The phenomenal increase in internet usage, catering to the dissemination of knowledge and expression, has also led to an increase in online hate speech. Online hate speech is anti-social communicative behavior, which leads to the threat and violence toward an individual or a group. …