From 7b7d35cdb648a255c01e3cbb12bd23c80ca8d703 Mon Sep 17 00:00:00 2001
From: Vladimir Malenovsky <vladimir.malenovsky@usherbrooke.ca>
Date: Wed, 24 May 2023 10:30:55 +0200
Subject: [PATCH] support for combining two samples of the same talker in each
 input item

---
 item_gen_configs/P800-6.yml                          | 12 +++++++-----
 .../generation/process_ism_items.py                  |  8 ++++----
 2 files changed, 11 insertions(+), 9 deletions(-)

diff --git a/item_gen_configs/P800-6.yml b/item_gen_configs/P800-6.yml
index ff337912..6d7a8e12 100644
--- a/item_gen_configs/P800-6.yml
+++ b/item_gen_configs/P800-6.yml
@@ -15,7 +15,7 @@ fs: 48000
 ### For Windows users: please use double back slash '\\' in paths and add '.exe' to executable definitions
 
 ### Input path to mono files
-input_path: "./items_mono"
+input_path: "./items_mono/trimmed"
 
 ### Output path for generated test items and metadata files
 output_path: "experiments/selection/P800-6/proc_input"
@@ -24,8 +24,8 @@ output_path: "experiments/selection/P800-6/proc_input"
 loudness: -26
 
 ### Pre-amble and Post-amble length in seconds (default = 0.0)
-# preamble: 0.5
-# postamble: 0.5
+preamble: 1.0
+postamble: 1.0
 
 ### Flag for adding low-level random background noise (amplitude +-4) instead of silence; default = false (silence)
 add_low_level_random_noise: true
@@ -52,16 +52,18 @@ scenes:
     a1: 
         name: "G1S1.wav"
         description: "Talker sitting at a table"
-        source: "m1_s1.wav"
+        source: ["m1_s1.wav", "m1_s7.wav"]
         azimuth: 0 
         elevation: 0 
+        overlap: -0.5
         
     a2: 
         name: "G6S2.wav"
         description: "Talker sitting at a table"
-        source: "f3_s2.wav"
+        source: ["f3_s2.wav", "f3_s8.wav"]
         azimuth: 60 
         elevation: 0 
+        overlap: -0.5
         
     a3: 
         name: "G5S3.wav"
diff --git a/ivas_processing_scripts/generation/process_ism_items.py b/ivas_processing_scripts/generation/process_ism_items.py
index 440f9273..cb8a46b8 100644
--- a/ivas_processing_scripts/generation/process_ism_items.py
+++ b/ivas_processing_scripts/generation/process_ism_items.py
@@ -102,10 +102,10 @@ def generate_ism_items(
         # repeat for all source files
         for i in range(N_sources):
             # parse parameters from the scene description
-            source_file = np.atleast_1d(scene["source"])[i]
-            source_azi = np.atleast_1d(scene["azimuth"])[i]
-            source_ele = np.atleast_1d(scene["elevation"])[i]
-
+            source_file = scene["source"][i] if isinstance(scene["source"], list) else scene["source"]   
+            source_azi = scene["azimuth"][i] if isinstance(scene["azimuth"], list) else scene["azimuth"]   
+            source_ele = scene["elevation"][i] if isinstance(scene["elevation"], list) else scene["elevation"]   
+            
             logger.info(
                 f"Encoding {source_file} at position(s) {source_azi},{source_ele}"
             )
-- 
GitLab