Large-scale speaker identification

A New Strategy of Direct Access for Speaker Identification System Based on Classification

“…Other work by Schmidt et al [4] uses Local Sensitive Hashing (LSH) and fast nearest neighbor search algorithm for speaker indexing. Schmidt proposed an indexing method using i- Vector.…”

Comparison of I-vector and GMM-UBM approaches to speaker identification with TIMIT and NIST 2008 databases in challenging environments

“…This section summarises the current work on I-vector and GMM-UBM approaches and other related work, alongside our previous work and other state of the art methods [14], [22], [12], [13], [23], [24], and [5]. According to Table IV, the handset used was G.712 type at 16 kHz, and all proposed noise measurements in this table were at SNR 30 dB and mixture size 256.…”

“…Nevertheless, this study lacked a large number of speakers, as only 50 self collected speakers were used. In [13], 1,000 speakers were selected from YouTube to construct an I-vector speaker identification framework, but this non-standard database did not include noisy conditions.…”

Evaluation of a speaker identification system with and without fusion using three databases in the presence of noise and handset effects

“…where, both i and j take values 1 and 2, therefore f weight ij takes one of four values f weight 11 , f weight 12 , f weight 13 , and f weight 22 , and f weight 11 is the linear combination of f 1 and g 1 , likewise f weight 12 is the linear combination of f 1 and g 2 and so on. For each f weight ij , ω β can take on one of four values, namely, ω β ∈ {0.9, 0.8, 0.77, 0.7} which is chosen to give empirically the best SIA.…”

“…However, the identification rate using the NIST 2003 database was poor. In [13], approximately 1000 speakers were selected and recordings were made, including in an acoustics room, with noise, and with varying microphone distance. However, the conditions were perhaps unfair and a non-standard database (derived from YouTube) was used.…”