Calibrated Prediction Intervals for Neural Network Regressors von Keren, Gil, Cummins, Nicholas, Schuller, Bjorn

Volltext

N-HANS: A neural network-based toolkit for in-the-wild audio enhancement von Liu, Shuo, Keren, Gil, Parada-Cabaleiro, Emilia, Schuller, Björn

Volltext

Analysis of loss functions for fast single-class classification von Keren, Gil, Sabato, Sivan, Schuller, Björn

Volltext

New Avenues in Audio Intelligence: Towards Holistic Real-life Audio Understanding von Schuller, Björn, Baird, Alice, Gebhard, Alexander, Amiriparian, Shahin, Keren, Gil, Schmitt, Maximilian, Cummins, Nicholas

Volltext

Emotion Recognition in Speech with Latent Discriminative Representations Learning von Han, Jing, Zhang, Zixing, Keren, Gil, Schuller, Björn

Volltext

ON DEFINABLE SKOLEM FUNCTIONS IN WEAKLY O-MINIMAL NONVALUATIONAL STRUCTURES von ELEFTHERIOU, PANTELIS E., HASSON, ASSAF, KEREN, GIL

Volltext

A Token-Wise Beam Search Algorithm for RNN-T von Keren, Gil

Volltext bestellen

A Token-Wise Beam Search Algorithm for RNN-T von Gil, Keren

Volltext

Token-Weighted RNN-T for Learning from Flawed Data von Keren, Gil, Zhou, Wei, Kalinli, Ozlem

Volltext bestellen

Faster Speech-LLaMA Inference with Multi-token Prediction von Raj, Desh, Keren, Gil, Jia, Junteng, Mahadeokar, Jay, Kalinli, Ozlem

Volltext bestellen

Efficient Streaming LLM for Speech Recognition von Jia, Junteng, Keren, Gil, Zhou, Wei, Lakomkin, Egor, Zhang, Xiaohui, Wu, Chunyang, Seide, Frank, Mahadeokar, Jay, Kalinli, Ozlem

Volltext bestellen

Token-Weighted RNN-T for Learning from Flawed Data von Gil, Keren, Zhou, Wei, Kalinli, Ozlem

Volltext

Towards Selection of Text-to-speech Data to Augment ASR Training von Liu, Shuo, Sarı, Leda, Wu, Chunyang, Keren, Gil, Shangguan, Yuan, Mahadeokar, Jay, Kalinli, Ozlem

Volltext bestellen

N-HANS: Introducing the Augsburg Neuro-Holistic Audio-eNhancement System von Liu, Shuo, Keren, Gil, Schuller, Björn

Volltext bestellen

M-BEST-RQ: A Multi-Channel Speech Foundation Model for Smart Glasses von Yang, Yufeng, Raj, Desh, Lin, Ju, Moritz, Niko, Jia, Junteng, Keren, Gil, Lakomkin, Egor, Huang, Yiteng, Donley, Jacob, Mahadeokar, Jay, Kalinli, Ozlem

Volltext bestellen

Single-Channel Speech Separation with Auxiliary Speaker Embeddings von Liu, Shuo, Keren, Gil, Schuller, Björn

Volltext bestellen

Convolutional RNN: an Enhanced Model for Extracting Features from Sequential Data von Keren, Gil, Schuller, Björn

Volltext bestellen

Faster Speech-LLaMA Inference with Multi-token Prediction von Raj, Desh, Gil, Keren, Jia, Junteng, Mahadeokar, Jay, Kalinli, Ozlem

Volltext

Scaling Speech Enhancement in Unseen Environments with Noise Embeddings von Keren, Gil, Han, Jing, Schuller, Björn

Volltext bestellen

AUDIO PROCESSING APPARATUS AND METHOD FOR DENOISING A MULTI-CHANNEL AUDIO SIGNAL von KEREN, Gil, LIU, Shuo, SCHULLER, Bjoern, TAGHIZADEH, Mohammad

Volltext bestellen