Spoken language recognition (SLR) refers to the automatic process used to determine the language present in a speech sample. SLR is an important task in its own right, for example, as a tool to analyze or categorize large amounts of multi-lingual data. Further, it is also an essential tool for selecting downstream applications in a work flow, for example, to chose appropriate speech recognition or machine translation models. SLR systems are usually composed of two stages, one where an embedding representing the audio sample is extracted and a second one which computes the final scores for each language. In this work, we approach the SLR task as a detection problem and implement the second stage as a probabilistic linear discriminant analysis (PLDA) model. We show that discriminative training of the PLDA parameters gives large gains with respect to the usual generative training. Further, we propose a novel hierarchical approach where two PLDA models are trained, one to generate scores for clusters of highly-related languages and a second one to generate scores conditional to each cluster. The final language detection scores are computed as a combination of these two sets of scores. The complete model is trained discriminatively to optimize a cross-entropy objective. We show that this hierarchical approach consistently outperforms the non-hierarchical one for detection of highly related languages, in many cases by large margins. We train our systems on a collection of datasets including over 100 languages, and test them both on matched and mismatched conditions, showing that the gains are robust to condition mismatch.

In this work, we assess the impact of vocal effort on discrimination and calibration performance of a state-of-the-art speaker recognition system. We analyze three levels of vocal effort (low, normal, and high) from the SRI-FRTIV corpus. We use a deep neural network (DNN) speaker embeddings system with probabilistic linear discriminant analysis (PLDA) and find that vocal effort variation significantly degrades system performance. We apply both mixture PLDA (mix-PLDA) and trial-based calibration with condition PLDA similarity (TBC-CPLDA) to improve system robustness. Our proposed approaches resulted in 18% and 33% relative improvement in discrimination and calibration performance respectively on the SRI-FRTIV corpus.

The output scores of most of the speaker recognition systems are not directly interpretable as stand-alone values. For this reason, a calibration step is usually performed on the scores to convert them into proper likelihood ratios, which have a clear probabilistic interpretation. The standard calibration approach transforms the system scores using a linear function trained using data selected to closely match the evaluation conditions. This selection, though, is not feasible when the evaluation conditions are unknown. In previous work, we proposed a calibration approach for this scenario called trial-based calibration (TBC). TBC trains a separate calibration model for each test trial using data that is dynamically selected from a candidate training set to match the conditions of the trial. In this work, we extend the TBC method, proposing: 1) a new similarity metric for selecting training data that result in significant gains over the one proposed in the original work; 2) a new option that enables the system to reject a trial when not enough matched data are available for training the calibration model; and 3) the use of regularization to improve the robustness of the calibration models trained for each trial. We test the proposed algorithms on a development set composed of several conditions and on the Federal Bureau of Investigation multi-condition speaker recognition dataset, and we demonstrate that the proposed approach reduces calibration loss to values close to 0 for most of the conditions when matched calibration data are available for selection, and that it can reject most of the trials for which relevant calibration data are unavailable.

The newly collected Speakers in the Wild (SITW) database was central to a text-independent speaker recognition challenge held as part of a special session at Interspeech 2016. The SITW database is composed of audio recordings from 299 speakers collected from open source media, with an average of 8 sessions per speaker. The recordings contain unconstrained or wild acoustic conditions, rarely found in large speaker recognition datasets, and multi-speaker recordings for both speaker enrollment and verification. This article provides details of the SITW speaker recognition challenge and analysis of evaluation results. There were 25 international teams involved in the challenge of which 11 teams participated in an evaluation track. Teams were tasked with applying existing and novel speaker recognition algorithms to the challenges associated with the real world conditions of SITW. We provide an analysis of some of the top performing systems submitted during the evaluation and provide future research directions. Copyright ©2016 ISCA.

This paper proposes a novel audio segmentation-by-classification system based on Factor Analysis (FA) with a channel compensation matrix for each class and scoring the fixed-length segments as the log-likelihood ratio between class/no-class. The scores are smoothed and the most probable sequence is computed with a Viterbi algorithm. The system described here is designed to segment and classify the audio files coming from broadcast programs into five different classes: speech (SP), speech with noise (SN), speech with music (SM), music (MU) or others (OT). This task was proposed in the Albayzin 2010 evaluation campaign. The system is compared with the winning system of the evaluation achieving lower error rate in SP and SN. These classes represent 3/4 of the total amount of the data. Therefore, the FA segmentation system gets a reduction in the average segmentation error rate.

Because of the popularity of online videos, there has been much interest in recent years in audio processing for the improvement of online video search. In this paper, we explore using acoustic concepts and spoken concepts extracted via audio segmentation/recognition and speech recognition respectively for Multimedia Event Detection (MED). To extract spoken concepts, a segmenter trained on annotated data from user videos segments the audio into three classes: speech, music, and other sounds. The speech segments are passed to an Automatic Speech Recognition (ASR) engine, and words from the 1-best ASR output, as well as posterior-weighted word counts collected from ASR lattices, are used as features to an SVM based classifier. Acoustic concepts are extracted using the 3-gram lattice counts of two Acoustic Concept Recognition (ACR) systems trained on 7 broad classes. MED results are reported on a subset of the NIST 2011 TRECVID data. We find that spoken concepts using lattices yield a 15% relative improvement in Average Pmiss (APM) over 1-best based features. Further, the proposed spoken concepts gave a 30% relative gain in APM over the ACR-based MED system using 7 classes. Lastly, we obtain an 8% relative APM improvement after score-level fusion of both concept types, showing the effective coupling of both approaches.